© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 16129
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日在
    -0.61
     in
    -0.54
    人在
    -0.46
    在
    -0.45
    Datuak
    -0.44
     into
    -0.43
     occupants
    -0.41
    在这种
    -0.41
     Nachbarn
    -0.40
     Bewohner
    -0.39
    POSITIVE LOGITS
     context
    1.05
     وفي
    1.00
     וב
    1.00
     manner
    0.93
     contexts
    0.91
     contexto
    0.83
     guise
    0.82
     contesto
    0.79
     realm
    0.77
     midst
    0.77
    Activations Density 1.934%

    No Known Activations