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. 3-GEMMASCOPE-RES-16K
    6. 8360
    Prev
    Next
    INDEX
    Explanations

    function calls related to obtaining instances or invoking specific operations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.76
    tableFuture
    -0.61
     ModelExpression
    -0.59
    rakt
    -0.58
     Legendre
    -0.58
    ழ்
    -0.58
     Higgs
    -0.57
     aprobado
    -0.55
    firebase
    -0.55
     bson
    -0.55
    POSITIVE LOGITS
    getInstance
    1.33
    ToolStrip
    1.15
    VersionUID
    0.77
    TagMode
    0.77
     initComponents
    0.75
    github
    0.70
    ActionListener
    0.69
     <<<<<<<<<<<<<<
    0.68
     getInstance
    0.68
    ruptedException
    0.66
    Activations Density 0.015%

    No Known Activations