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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 151
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to properties and structures within scientific or mathematical contexts

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

    concepts related to genetics, social structures, and molecular biology

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

    scientific and technical terms

    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
    Vidite
    -0.88
     Administrativna
    -0.77
    Datuak
    -0.76
    NUMX
    -0.75
    `,
    
    -0.74
    Personensuche
    -0.74
    ViewFeatures
    -0.73
    Xna
    -0.73
    '));
    
    -0.72
    ".
    
    -0.70
    POSITIVE LOGITS
    mode
    0.47
    se
    0.46
    providedIn
    0.45
     rule
    0.45
     ilan
    0.42
     Audiodateien
    0.42
     concept
    0.42
    MathML
    0.42
    antMatchers
    0.41
     Theil
    0.40
    Activations Density 0.476%

    No Known Activations