© 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
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3055
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize specificity, distinction, or notable characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Identyfik
    -0.37
     according
    -0.35
     whilst
    -0.34
    "....
    -0.33
     ""){
    -0.33
     noOf
    -0.32
     ()=>{
    -0.31
    참고
    -0.31
     ''){
    -0.30
     ‘’
    -0.30
    POSITIVE LOGITS
    StoryboardSegue
    0.73
     חיצוניים
    0.72
    AnchorStyles
    0.61
     AssemblyCulture
    0.60
     consultato
    0.59
     Normdatei
    0.55
     مشين
    0.54
    awtextra
    0.54
     État
    0.52
    hyrchwyd
    0.52
    Activations Density 0.659%

    No Known Activations