© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6780
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to family law and child custody

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Terms related to legal or residence status

    np_acts-logits-general · gemini-2.0-flash

    child citizenship and residence born out of wedlock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     back
    -0.35
     ahead
    -0.32
     fast
    -0.31
     y
    -0.30
     good
    -0.29
     flat
    -0.28
    D
    -0.28
     hundreds
    -0.28
    y
    -0.28
     horrible
    -0.27
    POSITIVE LOGITS
    MigrationBuilder
    0.92
     ModelExpression
    0.80
     Normdatei
    0.79
     onCreateView
    0.77
    <unused3>
    0.72
    [@BOS@]
    0.72
    <unused41>
    0.72
    <unused79>
    0.72
    <unused68>
    0.72
    <pad>
    0.72
    Activations Density 0.684%

    No Known Activations