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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 11285
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    errHandler
    -0.66
    fxml
    -0.56
    ymce
    -0.55
    mybatisplus
    -0.52
     ExecuteAsync
    -0.52
    ActionCreators
    -0.51
     allegedly
    -0.51
    헌
    -0.51
    calculus
    -0.51
    NameInMap
    -0.49
    POSITIVE LOGITS
    initWithFrame
    0.55
     itſelf
    0.54
     tartalomajánló
    0.53
     Biv
    0.53
     Pyrr
    0.52
     $_"
    0.50
     rehearing
    0.49
     yourselves
    0.49
     Mov
    0.49
     myſelf
    0.49
    Activations Density 0.884%

    No Known Activations