© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8157
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and their associated initiatives

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

    Follows a company or organization name

    np_acts-logits-general · gemini-2.0-flash

    Toronto places and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    例句
    -0.53
    
    -0.45
    codable
    -0.43
     cherchés
    -0.42
    εια
    -0.42
    TextWatcher
    -0.41
    geben
    -0.41
    zzard
    -0.40
     gegeven
    -0.40
    indépendance
    -0.39
    POSITIVE LOGITS
    GeneratedCode
    0.72
    kháu
    0.65
    URLException
    0.64
    цездатний
    0.63
     الرياضيه
    0.62
    aarrggbb
    0.61
     Oss
    0.60
     تضيفلها
    0.57
    niająca
    0.57
    nologue
    0.56
    Activations Density 0.121%

    No Known Activations