© 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. 13062
    Prev
    Next
    INDEX
    Explanations

    punctuation and numerical values, indicating it is focused on formatting and data representation

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

    numbers and code snippets

    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
     tủ
    -0.35
     thousands
    -0.34
     makl
    -0.33
    感
    -0.32
     rive
    -0.31
     ş
    -0.30
    PackageInfo
    -0.29
     jed
    -0.29
    führer
    -0.29
     Kopf
    -0.29
    POSITIVE LOGITS
    +#+#
    0.63
    rungsseite
    0.59
     ExecuteAsync
    0.55
    ReusableCell
    0.55
    yntaxException
    0.54
    例句
    0.51
    urten
    0.50
    ädchen
    0.48
     corretto
    0.48
    原始内容存档于
    0.47
    Activations Density 0.272%

    No Known Activations