Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8973
    Prev
    Next
    INDEX
    Explanations

    specific technical terminology related to systems and infrastructure

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

    common phrases after words

    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
    StoryboardSegue
    -0.53
    kijken
    -0.49
    Comté
    -0.47
    Приятного
    -0.47
    featureID
    -0.46
    aarrggbb
    -0.46
     TestBed
    -0.45
     alluminio
    -0.44
     виправивши
    -0.43
    ForValue
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.51
    OCCURRED
    0.46
    awtextra
    0.42
     ***!
    0.42
    oplayer
    0.37
    <%@
    0.36
    SourceChecksum
    0.36
    ➯
    0.36
    󠁬
    0.36
     уч
    0.35
    Activations Density 0.084%

    No Known Activations