© 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. 65156
    Prev
    Next
    INDEX
    Explanations

    phrases related to project planning and assessments

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

    project planning and design

    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
     bubuk
    -0.35
    newPassword
    -0.34
     estrenar
    -0.34
     répar
    -0.34
    rost
    -0.34
    index
    -0.33
     powdered
    -0.32
     index
    -0.32
     réparation
    -0.32
    onacci
    -0.31
    POSITIVE LOGITS
     preliminary
    0.71
     detailed
    0.68
    detailed
    0.65
    Detailed
    0.65
    Preliminary
    0.65
     Detailed
    0.63
     Preliminary
    0.63
     feasibility
    0.62
    liminary
    0.61
    conceptual
    0.61
    Activations Density 0.028%

    No Known Activations