© 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. 20-GEMMASCOPE-RES-131K
    11. 29967
    Prev
    Next
    INDEX
    Explanations

    blocks of comment or documentation notation typically used in code

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

    code comments and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ekor
    -0.39
    Slf
    -0.37
     "@/
    -0.37
     상세
    -0.36
     aranha
    -0.36
    DataBind
    -0.36
     vogli
    -0.35
    (&:
    -0.35
    iVar
    -0.35
     destinés
    -0.35
    POSITIVE LOGITS
    *************
    1.95
    ************
    1.03
     autorytatywna
    0.93
    **********
    0.91
    ***********
    0.89
    ftagPool
    0.88
     CreateTagHelper
    0.88
     незавершена
    0.84
    **************
    0.79
    *********
    0.75
    Activations Density 0.000%

    No Known Activations