© 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. 116134
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accountability or obligation

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

    responsibility of licensees

    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
     surla
    -0.65
    ########.
    -0.58
    msleep
    -0.57
    Hentet
    -0.54
     متعلقه
    -0.54
    hilangan
    -0.54
    WebElementEntity
    -0.54
     informée
    -0.53
    MessageOf
    -0.48
    reportWebVitals
    -0.48
    POSITIVE LOGITS
    AutoScaleMode
    0.49
     AssemblyProduct
    0.39
    帖最后由
    0.36
    complexContent
    0.36
     ivelany
    0.34
     SDLK
    0.31
     licensee
    0.30
    RenderAtEndOf
    0.30
    Dro
    0.29
    DOUT
    0.29
    Activations Density 0.000%

    No Known Activations