© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 58625
    Prev
    Next
    INDEX
    Explanations

    integer data types and variable declarations

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

    integer type declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.39
     tard
    -0.38
    fclose
    -0.38
    ℠
    -0.38
    isDefault
    -0.37
     Therapeutic
    -0.37
    Tämä
    -0.36
     Floating
    -0.36
     ®
    -0.35
    Cierre
    -0.35
    POSITIVE LOGITS
    MigrationBuilder
    0.71
     int
    0.67
    int
    0.65
    Int
    0.53
     Int
    0.52
     snippetHide
    0.50
    Diweddarwch
    0.49
    afficheront
    0.49
     Chwiliwch
    0.48
    Източници
    0.48
    Activations Density 0.011%

    No Known Activations