© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14249
    Prev
    Next
    INDEX
    Explanations

    references to icons and graphical elements

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

    mentions of icons and other image assets in web or code snippets.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "icon" in file paths or variable names, particularly in technical contexts like HTML image tags or code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     (
    -0.45
     urma
    -0.42
    ExtendWith
    -0.41
    __':
    -0.41
    веси
    -0.40
     Washburn
    -0.40
    (!)
    -0.40
     (!
    -0.40
    eningen
    -0.39
    inigte
    -0.38
    POSITIVE LOGITS
     Icon
    1.10
     icon
    1.07
    Icon
    1.00
     Symbol
    1.00
     SYMBOL
    0.97
     symbol
    0.95
    Symbol
    0.94
     ICON
    0.94
    ymbol
    0.94
     icons
    0.93
    Activations Density 0.048%

    No Known Activations