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. 20-GEMMASCOPE-RES-16K
    6. 16197
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific syntactical structures used in programming code

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

    Code syntax punctuators

    np_acts-logits-general · gemini-2.0-flash

    closing brackets and semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.76
    buttonBar
    -0.65
     Uran
    -0.64
     **/
    
    -0.62
    CloseOperation
    -0.62
     HttpNotFound
    -0.60
    thday
    -0.59
    PreferredItem
    -0.58
    AsUp
    -0.57
     Efq
    -0.56
    POSITIVE LOGITS
    ↵
    0.64
    skjaer
    0.52
     semula
    0.52
    الدراسه
    0.52
    GEBURTSDATUM
    0.49
    EndInit
    0.48
    ularia
    0.48
     voraus
    0.45
    }());
    0.45
    jíma
    0.45
    Activations Density 0.022%

    No Known Activations