© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 38277
    Prev
    Next
    INDEX
    Explanations

    the presence of verbs indicating actions or decisions, particularly in past and present forms

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

    do not, did not, does not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.35
    mtrl
    -0.35
    styleType
    -0.33
    ToBe
    -0.32
     Schnell
    -0.30
     Sap
    -0.29
     Úl
    -0.29
     Geb
    -0.29
    wor
    -0.29
    InitVars
    -0.29
    POSITIVE LOGITS
     not
    0.67
     initComponents
    0.55
     NSCoder
    0.54
    playa
    0.54
    rungsseite
    0.52
    acamata
    0.52
    parseColor
    0.52
    ebenarnya
    0.52
    síða
    0.52
     nabíz
    0.50
    Activations Density 0.054%

    No Known Activations