© 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. 8934
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and entities along with their associated contexts

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

    Tokens after numbers

    np_acts-logits-general · gemini-2.0-flash

    Japanese names or terms

    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
     للاسماء
    -0.64
     مشين
    -0.51
     juridiques
    -0.50
    AISSEE
    -0.49
    expandindo
    -0.49
     knex
    -0.48
     jadx
    -0.48
     StatefulWidget
    -0.48
     getItemId
    -0.48
    etragen
    -0.47
    POSITIVE LOGITS
     appunto
    0.44
     تضيفلها
    0.42
     eben
    0.35
    出版年
    0.35
     obviously
    0.35
    jsxFileName
    0.34
    (@"%@",
    0.34
     sumpay
    0.33
    undef
    0.31
    webElementXpaths
    0.31
    Activations Density 0.289%

    No Known Activations