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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16005
    Prev
    Next
    INDEX
    Explanations

    references to materials and methods related to sample collection and extraction procedures

    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
    endpush
    -0.69
    principalColumn
    -0.62
     lenker
    -0.56
    elemField
    -0.54
    RenderAtEndOf
    -0.53
     grünen
    -0.52
     Vordergrund
    -0.50
     tangerang
    -0.50
    StructEnd
    -0.50
    AutoField
    -0.50
    POSITIVE LOGITS
    antin
    0.41
     rubbing
    0.38
    litt
    0.37
    kyo
    0.36
    WriteAttribute
    0.36
    IGNORE
    0.35
     아
    0.35
    antis
    0.35
     Signalez
    0.34
     Ath
    0.34
    Activations Density 0.696%

    No Known Activations