© 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. 2-GEMMASCOPE-RES-16K
    11. 2518
    Prev
    Next
    INDEX
    Explanations

    specific genetic sequences and markers related to DNA and protein analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.29
    OGND
    -0.27
    mybatisplus
    -0.27
     source
    -0.27
     litro
    -0.26
    elementType
    -0.25
     zune
    -0.25
     Kono
    -0.23
    ình
    -0.23
     Clemente
    -0.23
    POSITIVE LOGITS
     Cay
    1.37
     Cad
    1.36
    Cad
    1.32
    Cay
    1.31
     ка
    1.31
     Kaj
    1.30
    Kaj
    1.28
     Cahill
    1.27
    CAD
    1.27
     CAD
    1.27
    Activations Density 0.633%

    No Known Activations