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. 2772
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate direction or change over time

    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
     navíc
    -0.53
    mayın
    -0.50
     zugleich
    -0.49
     wikipagina
    -0.49
     giudizio
    -0.49
     preocupes
    -0.47
    참고
    -0.47
     frattempo
    -0.47
     berikutnya
    -0.45
     myö
    -0.45
    POSITIVE LOGITS
    '][]
    0.82
    enumi
    0.82
     nahilalakip
    0.81
    */,
    0.77
    ")]
    
    0.75
    AddTagHelper
    0.75
    клопе
    0.71
    :+:
    0.71
     लेकर
    0.71
    ']);
    
    0.71
    Activations Density 0.133%

    No Known Activations