© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33148
    Prev
    Next
    INDEX
    Explanations

    terms related to teamwork and collaboration

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

    user and developer edits

    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
    ElementException
    -0.56
    awaiter
    -0.56
    YourGuide
    -0.54
     المعيارى
    -0.52
     kentang
    -0.50
    OuterAlt
    -0.49
    enterOuterAlt
    -0.48
     soledad
    -0.48
     FormGroup
    -0.48
    -------
    -0.47
    POSITIVE LOGITS
    AddHtmlAttribute
    0.44
    Shared
    0.38
    shared
    0.38
     Shared
    0.36
     wi
    0.34
     parties
    0.34
    jedis
    0.33
     shared
    0.31
    team
    0.31
     Syndicate
    0.31
    Activations Density 0.052%

    No Known Activations