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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9906
    Prev
    Next
    INDEX
    Explanations

    function call patterns and their related parameters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ########.
    -0.65
    ();
    
    
    -0.55
    ...",
    -0.55
    OGND
    -0.53
    ...?"
    -0.50
    '],
    
    -0.49
    ...".
    -0.48
     **/
    
    -0.48
    ?!"
    -0.47
     /></
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
     {
    0.73
    MessageTagHelper
    0.69
    MLLoader
    0.67
    DockStyle
    0.67
     propOrder
    0.63
    XmlAccessType
    0.61
    migrationBuilder
    0.61
    extAlignment
    0.60
    InputBorder
    0.59
    Activations Density 0.022%

    No Known Activations