© 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. 12998
    Prev
    Next
    INDEX
    Explanations

    repeated patterns of certain characters, primarily focusing on specific sequences of 'u's and 'x's

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

    currency codes and abbreviations

    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
     OMITBAD
    -0.44
    a
    -0.39
    ỡng
    -0.37
     Pfar
    -0.36
    $_['
    -0.36
    AndEndTag
    -0.35
    sidian
    -0.34
     Sécurité
    -0.33
     vôtre
    -0.33
     nasled
    -0.33
    POSITIVE LOGITS
     ***!
    0.59
    <bos>
    0.57
    Erstellt
    0.52
    发表于
    0.52
    GroupLayout
    0.52
     referrerpolicy
    0.49
     GenerationType
    0.49
     bVar
    0.49
    croll
    0.48
     Strat
    0.48
    Activations Density 0.031%

    No Known Activations