© 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. 72456
    Prev
    Next
    INDEX
    Explanations

    predicates and their associated modifiers

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

    there's no

    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
     مشين
    -0.43
     }}}{
    -0.35
    匿名使用者
    -0.34
     INTELL
    -0.34
    帖最后由
    -0.34
     endblock
    -0.33
    IntoConstraints
    -0.33
    Controllo
    -0.33
     owner
    -0.33
     فريبيس
    -0.33
    POSITIVE LOGITS
    rouvez
    0.61
    Certain
    0.53
     Certain
    0.53
    certain
    0.52
     kaikki
    0.50
     Paglinawan
    0.49
    iastes
    0.49
    nothing
    0.49
    iettivo
    0.48
     semmi
    0.46
    Activations Density 0.061%

    No Known Activations