Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6704
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.42
     actionMode
    -0.40
    SerializedName
    -0.38
     scattata
    -0.37
    complexType
    -0.36
     StatelessWidget
    -0.35
    SystemColors
    -0.35
    ConstraintMaker
    -0.35
     señores
    -0.34
     scă
    -0.34
    POSITIVE LOGITS
     POLICE
    0.76
     Police
    0.75
     policemen
    0.74
     police
    0.73
    police
    0.71
     policeman
    0.71
    Police
    0.71
     Policing
    0.67
    警察
    0.60
     cops
    0.60
    Activations Density 0.703%

    No Known Activations