© 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. 70677
    Prev
    Next
    INDEX
    Explanations

    references to academic citations and their formatting

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

    conferences with page numbers

    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
     utafitiHapana
    -0.48
    utilisons
    -0.40
     basal
    -0.39
    Personensuche
    -0.37
     المعيارى
    -0.36
    CIUDAD
    -0.35
    ього
    -0.34
     iprot
    -0.34
    cámara
    -0.34
    TokenNameCOMMA
    -0.34
    POSITIVE LOGITS
    endregion
    0.59
    oredCriteria
    0.53
     snippetHide
    0.52
    олові
    0.47
    msgTypes
    0.46
     ExecuteAsync
    0.45
     noDo
    0.44
     delegate
    0.43
    enic
    0.43
     CURIAM
    0.43
    Activations Density 0.023%

    No Known Activations