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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 63309
    Prev
    Next
    INDEX
    Explanations

    aspects of change and conflict in personal narratives

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

    when the value of crownvetch wasn’t worth

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Autoritní
    -0.56
     الرياضيه
    -0.48
    Personendaten
    -0.47
     hasNext
    -0.46
    例句
    -0.46
    énario
    -0.45
    RTEE
    -0.44
     ModelExpression
    -0.43
    Dtor
    -0.42
     iprot
    -0.41
    POSITIVE LOGITS
    IsMutable
    0.44
    hoedd
    0.38
     invasive
    0.35
     كومونز
    0.34
    æld
    0.34
     deterioration
    0.33
    AddHtmlAttribute
    0.33
    WritableDatabase
    0.32
     mysteriously
    0.32
     Lijst
    0.32
    Activations Density 0.037%

    No Known Activations