Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1268
    Prev
    Next
    INDEX
    Explanations

    elements that define code structure and initialization in programming

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

    code structures related to initialization in programming

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

    keywords and code structure

    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
     kasarigan
    -0.77
    featureID
    -0.64
     jLabel
    -0.63
    LookAnd
    -0.60
    ContentAsync
    -0.60
     Signalez
    -0.59
     jsPsych
    -0.59
    Viitteet
    -0.58
    TagMode
    -0.57
     autocollant
    -0.56
    POSITIVE LOGITS
     class
    0.54
    dataclass
    0.50
     للمعارف
    0.49
    ={[
    0.45
    สบ
    0.44
    MemoryWarning
    0.43
    JsonInclude
    0.42
    memset
    0.42
    GraphicsUnit
    0.42
    |}\
    0.41
    Activations Density 0.087%

    No Known Activations