© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 796
    Prev
    Next
    INDEX
    Explanations

    the occurrence of proper nouns or names

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

    Tokens starting with "Ke" referring to people or publications

    np_acts-logits-general · gemini-2.0-flash

    words starting with Ke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    LookAnd
    -0.79
     purpoſe
    -0.78
     itſelf
    -0.72
    aarrggbb
    -0.71
    lessly
    -0.71
     Punj
    -0.70
     leſs
    -0.70
     plex
    -0.69
     autorytatywna
    -0.68
     ddelweddau
    -0.68
    POSITIVE LOGITS
     combineReducers
    0.52
    withIdentifier
    0.52
     Ke
    0.51
     WebDriverWait
    0.48
     kele
    0.45
    ke
    0.43
     publik
    0.42
    Kev
    0.41
    Ke
    0.41
    /******/
    0.41
    Activations Density 0.070%

    No Known Activations