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. 15729
    Prev
    Next
    INDEX
    Explanations

    elements related to technical or programming contexts

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

    Mathematical or programming expressions

    np_acts-logits-general · gemini-2.0-flash

    code and punctuation

    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
     defaultstate
    -0.78
    XmlAccessType
    -0.69
    alyptus
    -0.64
    NOPQRST
    -0.61
    TagHelpers
    -0.57
    uxxxx
    -0.56
     nonatomic
    -0.56
    WebElementEntity
    -0.55
    TProtocol
    -0.54
    fastjson
    -0.54
    POSITIVE LOGITS
    ?
    
    0.63
     **/
    
    0.63
    .";
    
    0.62
    .")
    
    0.62
     //
    
    0.59
    ()]);
    0.59
    contentLoaded
    0.59
    "]
    
    0.58
    !")
    
    0.57
     »)
    0.57
    Activations Density 4.896%

    No Known Activations