© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104769
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about obtaining or clarifying information and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    principalColumn
    -0.77
    +#+
    -0.77
     AssemblyCulture
    -0.77
     AssemblyCompany
    -0.76
    uxxxx
    -0.74
    inSlope
    -0.72
    帖最后由
    -0.71
    Попис
    -0.67
     snippetHide
    -0.66
     OMITBAD
    -0.66
    POSITIVE LOGITS
     im
    0.40
     HOW
    0.39
     diab
    0.38
     where
    0.37
     she
    0.36
     Refer
    0.36
     Grin
    0.36
     pend
    0.35
     report
    0.35
     test
    0.35
    Activations Density 0.070%

    No Known Activations