© 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. 0-GEMMASCOPE-RES-16K
    11. 13653
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "shark" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vogt
    -0.37
     Farrar
    -0.30
     Eaton
    -0.30
    ôtel
    -0.29
     aDecoder
    -0.29
    lcccc
    -0.28
    渍
    -0.28
    enegal
    -0.28
    BASEPATH
    -0.28
    >`;
    -0.27
    POSITIVE LOGITS
     SH
    2.16
    Sh
    2.16
     Sh
    2.14
     sh
    2.13
    SH
    2.05
    sh
    1.95
     shunt
    1.70
     Sher
    1.66
     Shu
    1.66
     Shi
    1.63
    Activations Density 0.933%

    No Known Activations