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. 2-GEMMASCOPE-RES-16K
    6. 15099
    Prev
    Next
    INDEX
    Explanations

    references to symbols in programming and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.60
     egne
    -0.59
     MSS
    -0.57
    devamını
    -0.57
     SST
    -0.56
    เภ
    -0.56
     $[-
    -0.56
    WriteAttribute
    -0.55
    hoeddwyd
    -0.54
    @[
    -0.54
    POSITIVE LOGITS
     symbol
    3.69
     symbols
    3.46
     Symbol
    3.34
    symbol
    3.33
    Symbol
    3.15
     Symbols
    3.14
     SYMBOL
    3.05
    symbols
    2.93
    Symbols
    2.88
    SYMBOL
    2.81
    Activations Density 0.042%

    No Known Activations