© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11328
    Prev
    Next
    INDEX
    Explanations

    situations involving police interactions and legal circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dafx
    -0.46
     verhe
    -0.38
    ViewImports
    -0.35
    interopRequire
    -0.34
     يتيمه
    -0.34
     intermedio
    -0.32
     Diretto
    -0.32
     yyr
    -0.32
    jamientos
    -0.32
    payee
    -0.31
    POSITIVE LOGITS
     police
    3.23
    police
    2.77
     Police
    2.69
    Police
    2.64
     POLICE
    2.53
     policemen
    2.28
     policía
    2.25
     Polizei
    2.22
    警察
    2.19
     policeman
    2.14
    Activations Density 0.838%

    No Known Activations