© 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
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1550
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and parameters related to coding or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ApiModelProperty
    -0.47
    rrggbb
    -0.43
    principalTable
    -0.40
    InputModule
    -0.39
     ExecuteAsync
    -0.39
    DBNull
    -0.38
     المعيارى
    -0.35
     للمعارف
    -0.35
    localctx
    -0.35
     MainAxisSize
    -0.34
    POSITIVE LOGITS
     itſelf
    0.49
     tranſ
    0.48
     zijne
    0.48
     enfans
    0.47
     aDecoder
    0.46
     betweenstory
    0.44
     ſy
    0.43
    شویی
    0.43
     ſtand
    0.43
     utaf
    0.42
    Activations Density 1.943%

    No Known Activations