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. 12-GEMMASCOPE-RES-16K
    6. 4965
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and function definitions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fracas
    -0.38
     giải
    -0.37
    Needless
    -0.36
     
    -0.36
    <eos>
    -0.35
     reconciled
    -0.35
     lotta
    -0.35
    let
    -0.35
    PROS
    -0.35
    <strong>
    -0.35
    POSITIVE LOGITS
     autorytatywna
    1.04
     Chwiliwch
    0.93
     disambiguazione
    0.90
    bibfield
    0.79
    VIAF
    0.79
    protoimpl
    0.78
    paksa
    0.77
     ErrIntOverflow
    0.75
    adeloupe
    0.73
     ſame
    0.72
    Activations Density 0.136%

    No Known Activations