© 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. 91216
    Prev
    Next
    INDEX
    Explanations

    words that indicate a sense of obligation or necessity

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

    mustaţǎ, ust, eust, aristi

    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
    st
    -0.34
    th
    -0.30
    t
    -0.29
    stream
    -0.28
    est
    -0.27
     ing
    -0.27
     orizz
    -0.27
     Gefang
    -0.26
    count
    -0.25
     Next
    -0.25
    POSITIVE LOGITS
    LookAnd
    0.69
     ExecuteAsync
    0.68
    LEn
    0.67
    MENAFN
    0.65
     kasarigan
    0.64
    GOTREF
    0.63
    oplayer
    0.62
    batore
    0.61
    bootstrapcdn
    0.61
    intios
    0.60
    Activations Density 0.025%

    No Known Activations