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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13587
    Prev
    Next
    INDEX
    Explanations

    various characters and symbols used in programming or coding syntax

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    writeFieldEnd
    -0.67
     незавершена
    -0.67
     nahilalakip
    -0.59
    astéroïdes
    -0.58
    CppCodeGen
    -0.58
    InitVars
    -0.56
     ویکی‌پدی
    -0.55
    contentLoaded
    -0.55
    Storia
    -0.55
    adpleegd
    -0.52
    POSITIVE LOGITS
    BeginContext
    0.67
    AnchorStyles
    0.64
     MainAxisSize
    0.63
     الحره
    0.62
     Flas
    0.60
     tallest
    0.59
     magistrates
    0.58
    izontal
    0.58
    erunner
    0.57
     magistrate
    0.57
    Activations Density 0.000%

    No Known Activations