© 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. 31-GEMMASCOPE-RES-131K
    6. 110868
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "often" used in various contexts

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

    Often describes usual occurrences

    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
    <0xDA>
    -0.48
    Ƚ
    -0.46
     GenerationType
    -0.46
     MenuView
    -0.45
    流石
    -0.44
    onInit
    -0.43
    EntityId
    -0.43
    yelidikan
    -0.42
    eleste
    -0.42
     possibly
    -0.42
    POSITIVE LOGITS
     times
    0.64
     genug
    0.63
    times
    0.61
     бывает
    0.53
    Times
    0.50
     referred
    0.49
     enough
    0.49
    mals
    0.49
     TIMES
    0.49
     overlooked
    0.46
    Activations Density 0.016%

    No Known Activations