© 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. 65744
    Prev
    Next
    INDEX
    Explanations

    lines of code related to setting up or managing HTTP requests and responses in programming

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

    Create, Parse, New in code

    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
    delete
    -1.30
     delete
    -1.24
     Delete
    -0.86
     deleting
    -0.85
     deletes
    -0.83
    Delete
    -0.75
     deletion
    -0.75
     Deletes
    -0.74
     Deleting
    -0.73
     DELETE
    -0.72
    POSITIVE LOGITS
     New
    0.46
    New
    0.42
     einzu
    0.42
     Dim
    0.42
     Ehr
    0.42
     păr
    0.41
    CopyWith
    0.40
    Err
    0.40
     Zum
    0.40
     Ramon
    0.39
    Activations Density 0.096%

    No Known Activations