© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105241
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements related to experiments or studies

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

    user

    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
     geisti
    -0.31
     persönlichen
    -0.29
     Wege
    -0.29
     persön
    -0.28
     oscuridad
    -0.27
     vielen
    -0.27
     persönliche
    -0.26
    impresa
    -0.26
     consigo
    -0.25
     Häuser
    -0.24
    POSITIVE LOGITS
    الحياه
    0.85
    rungsseite
    0.84
    IsContent
    0.82
     <<<<<<<<<<<<<<
    0.76
    новништво
    0.76
    matchCondition
    0.76
     disponibilités
    0.71
    TagMode
    0.71
     للمعارف
    0.70
    BufferException
    0.69
    Activations Density 0.016%

    No Known Activations