© 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. 86700
    Prev
    Next
    INDEX
    Explanations

    references to file paths or directory structures in code

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

    google, path, bin, io, web addresses

    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
    ďaka
    -0.42
     být
    -0.40
    プリング
    -0.40
    transQ
    -0.40
     gereken
    -0.40
     takı
    -0.39
     australiano
    -0.39
     perlindungan
    -0.39
     başına
    -0.39
    พัก
    -0.38
    POSITIVE LOGITS
    __*/
    0.65
     FontWeight
    0.64
     scraper
    0.62
    spath
    0.59
    GOTREF
    0.59
     bible
    0.58
    ſchaft
    0.58
     fread
    0.57
    ruguay
    0.56
     Adele
    0.56
    Activations Density 0.001%

    No Known Activations