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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 10244
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    url, mathematical operators, and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')->
    -1.00
    ")->
    -0.89
    ))->
    -0.77
    ())->
    -0.72
    ')";
    -0.67
    '])->
    -0.67
    ']->
    -0.66
    )->
    -0.66
    "]=
    -0.63
    )))
    
    -0.63
    POSITIVE LOGITS
     ===
    0.88
     eslint
    0.82
     !==
    0.81
     TypeScript
    0.70
     Sequelize
    0.69
    (`${
    0.66
    eslint
    0.65
     &&
    0.65
    console
    0.64
     ||
    0.64
    Activations Density 0.269%

    No Known Activations