© 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. 58588
    Prev
    Next
    INDEX
    Explanations

    references to the initialization method in Python, specifically related to Django framework files

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

    constructor or initialization

    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
     unknownFields
    -0.37
    ressee
    -0.36
    たとえば
    -0.35
     blocks
    -0.34
     ganzen
    -0.33
     miała
    -0.33
    deutig
    -0.33
     informée
    -0.33
     fácilmente
    -0.33
    itteet
    -0.33
    POSITIVE LOGITS
    存于互联网档案馆
    0.57
    glEnd
    0.48
    gnore
    0.48
    JsonKey
    0.47
     IndexPath
    0.46
     ModelExpression
    0.45
    pyx
    0.44
    mainloop
    0.44
    Jeep
    0.43
     []).
    0.43
    Activations Density 0.006%

    No Known Activations