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 - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10249
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure, particularly related to layout and positioning in UI design

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

    Programming/Math related symbols

    np_acts-logits-general · gemini-2.0-flash

    parentheses containing coordinates or numbers

    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
    dorff
    -0.57
     Betracht
    -0.51
    newcommand
    -0.50
     kész
    -0.49
    den
    -0.49
    cetines
    -0.48
    =[]
    -0.48
     elkaar
    -0.47
    Carcinogenicity
    -0.45
    mybatisplus
    -0.45
    POSITIVE LOGITS
    CloseOperation
    0.75
     jScrollPane
    0.74
     Réponses
    0.74
    DockStyle
    0.74
     виправивши
    0.71
    IntoConstraints
    0.71
    awtextra
    0.70
    </caption>
    0.69
    ArgsConstructor
    0.69
    GEBURTS
    0.66
    Activations Density 0.039%

    No Known Activations