© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 81410
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations

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

    LaTeX math environments

    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
     Syrie
    -0.36
    rishnan
    -0.36
     pañ
    -0.36
    weilen
    -0.35
     ferien
    -0.35
     Aircraft
    -0.34
    oluene
    -0.33
    Toponymie
    -0.33
     Flughafen
    -0.33
    $_['
    -0.32
    POSITIVE LOGITS
    WithIOException
    0.68
    存于互联网档案馆
    0.66
     Numerade
    0.64
    httphttps
    0.64
     lenker
    0.62
     snippetHide
    0.62
     informée
    0.61
    Rhestr
    0.60
     للمعارف
    0.60
    WriteLiteral
    0.57
    Activations Density 0.002%

    No Known Activations