© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14562
    Prev
    Next
    INDEX
    Explanations

    the names of types of sharks.

    oai_token-act-pair · gemini-1.5-flashTriggered by @johnny

    food and beverage items.

    oai_token-act-pair · gemini-1.5-proTriggered by @johnny

    words and phrases related to specific types of sharks and reptiles.

    oai_token-act-pair · gpt-4oTriggered by @johnny

    Words related to aquatic animals, particularly predators like sharks and crocodiles, are significant, often accompanied by details on their behavior, environment, or species-specific traits.

    eleuther_acts_top20 · gpt-4oTriggered by @johnny

    information related to specific individuals and their activities or characteristics.

    oai_token-act-pair · gpt-3.5-turboTriggered by @johnny

    references to sharks and crocodiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calef
    -0.34
    yntaxException
    -0.33
     rotu
    -0.32
    subplots
    -0.31
    fördert
    -0.31
     MainAxisSize
    -0.30
     Muni
    -0.30
    shl
    -0.30
     wagon
    -0.30
     Corre
    -0.30
    POSITIVE LOGITS
     Coconut
    1.27
     coconut
    1.24
    Coconut
    1.16
    coconut
    1.14
     Florida
    1.09
     Miami
    1.02
    Florida
    1.02
     mangrove
    1.01
    conuts
    0.97
     kokos
    0.96
    Activations Density 0.673%

    No Known Activations