© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 24642
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and methods for managing collections

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

    package update property assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.70
     ویکی‌پدی
    -0.69
     فريبيس
    -0.67
    aarrggbb
    -0.65
     autorytatywna
    -0.65
    EndContext
    -0.64
     ब्रेकडाउन
    -0.64
    Diweddarwch
    -0.63
    Chham
    -0.63
     noDo
    -0.63
    POSITIVE LOGITS
    ↵
    0.49
     =>
    0.42
     {
    0.40
    (){
    0.39
    ():
    0.37
    ()
    0.35
     then
    0.35
    </h3>
    0.34
     A
    0.34
     fleuve
    0.34
    Activations Density 0.005%

    No Known Activations