© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13747
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting within complex written content

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

    Code, math, or obscure technical language

    np_acts-logits-general · gemini-2.0-flash

    deno or, breast, abusive, estoppel

    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
    ########.
    -0.58
    AutoScaleMode
    -0.54
    AndEndTag
    -0.52
    EndContext
    -0.50
    IntoConstraints
    -0.49
    PerformLayout
    -0.47
    әрмәләр
    -0.46
    TypedDataSet
    -0.46
    printStackTrace
    -0.45
     initComponents
    -0.45
    POSITIVE LOGITS
     Grüsse
    0.44
    thoven
    0.43
    */),
    0.41
    ɕ
    0.41
    Few
    0.41
    NECT
    0.40
    apimachinery
    0.40
    ❉
    0.40
    PostBack
    0.39
    abetes
    0.39
    Activations Density 1.271%

    No Known Activations