© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 711
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or segments in the document

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

    the presence of the beginning of a new document or paragraph

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

    programming functions and code

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    setVerticalGroup
    -0.77
    IntoConstraints
    -0.75
     للمعارف
    -0.72
    twimg
    -0.70
    Rohy
    -0.70
     CURIAM
    -0.69
    Viki
    -0.69
    LabelTagHelper
    -0.69
    
    -0.68
    Vidite
    -0.66
    POSITIVE LOGITS
    ()=>{
    0.58
    async
    0.58
     async
    0.55
     function
    0.54
     ()
    0.54
    function
    0.49
    <tbody>
    0.47
    ()
    0.47
     ()=>{
    0.41
     =>{
    0.41
    Activations Density 0.009%

    No Known Activations