© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6602
    Prev
    Next
    INDEX
    Explanations

    terms related to health, functionality, and programming structure

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

    Code, math, or special characters

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical expressions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    InjectAttribute
    -0.54
     useState
    -0.46
    FontOfSize
    -0.43
     caract
    -0.43
    IntoConstraints
    -0.43
     hemma
    -0.42
    NSIndexPath
    -0.42
    parsedMessage
    -0.42
    kegaard
    -0.41
     spé
    -0.41
    POSITIVE LOGITS
     <=",
    0.63
     فريبيس
    0.57
    RTLR
    0.51
    AddTagHelper
    0.51
    EReference
    0.48
    Filmographie
    0.43
    Trama
    0.43
    Filmografia
    0.42
     linkovi
    0.41
     ***!
    0.41
    Activations Density 1.502%

    No Known Activations