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

    Neuronpedia

    APICircuit 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. 11002
    Prev
    Next
    INDEX
    Explanations

    event-related programming structures and parameters in code

    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
    featureID
    -0.65
     Bambi
    -0.62
    RegistryLite
    -0.60
    ValueStyle
    -0.60
    EqualsAnd
    -0.58
    AccessorTable
    -0.58
     nowrap
    -0.57
    AssignableFrom
    -0.57
    OSPH
    -0.57
    WriteAttribute
    -0.57
    POSITIVE LOGITS
    UTC
    0.95
     os
    0.92
     Os
    0.91
     bea
    0.82
    Os
    0.77
    ceğine
    0.76
     во
    0.69
    beginTransaction
    0.69
     Bea
    0.69
     Osborne
    0.66
    Activations Density 0.035%

    No Known Activations