Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 66436
    Prev
    Next
    INDEX
    Explanations

    details related to competition results and placement

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

    winner or place

    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
    FunctionFlags
    -0.47
    TargetException
    -0.37
    poel
    -0.36
    MessageOf
    -0.35
    RTSN
    -0.35
     laquelle
    -0.33
    ritsar
    -0.33
     escala
    -0.33
    Noon
    -0.33
     której
    -0.33
    POSITIVE LOGITS
    clerview
    0.53
    Personendaten
    0.52
    parametrize
    0.51
    NamedQueries
    0.49
    šķ
    0.49
    reportWebVitals
    0.49
    <!--[
    0.48
    aarrggbb
    0.47
    ⎧
    0.47
     <=",
    0.46
    Activations Density 0.003%

    No Known Activations