© 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. 47698
    Prev
    Next
    INDEX
    Explanations

    words indicative of specific conditions or attributes being discussed or measured

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

    tokens following prepositions and conjunctions

    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
     CanadaChoose
    -0.68
     autorytatywna
    -0.65
    Бахар
    -0.63
    +#+#
    -0.58
     Administrativna
    -0.56
     TextAppearance
    -0.55
     مرئيه
    -0.55
     verſ
    -0.54
     ſou
    -0.54
    drawSprites
    -0.54
    POSITIVE LOGITS
    uxxxx
    0.56
    InjectAttribute
    0.54
    .?
    0.39
     tevens
    0.38
     jadx
    0.37
    !.
    0.36
    .,
    0.36
     vrouw
    0.35
    adze
    0.34
    ?.
    0.34
    Activations Density 0.059%

    No Known Activations