© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101718
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic texts

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

    bibliographic citation markers

    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
    UserScript
    -0.60
    initState
    -0.47
    run
    -0.45
     currentState
    -0.44
     Outs
    -0.44
    StateChanged
    -0.44
     Moreau
    -0.44
    force
    -0.43
     Kars
    -0.43
    state
    -0.43
    POSITIVE LOGITS
     bib
    0.91
     Bib
    0.90
    Bib
    0.89
     bibliography
    0.82
    bib
    0.80
     bibliographic
    0.78
     BIB
    0.76
     bibli
    0.72
     Bibli
    0.72
    Bibli
    0.71
    Activations Density 0.023%

    No Known Activations