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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3114
    Prev
    Next
    INDEX
    Explanations

    components of computer programming or markup language structures

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

    Code-related keywords or names

    np_acts-logits-general · gemini-2.0-flash

    code snippets and licenses

    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
     太郎
    -0.57
    bukkit
    -0.56
    '])){
    
    -0.56
    mappedBy
    -0.55
    '){
    
    -0.54
    SurfaceView
    -0.53
    angliski
    -0.53
    itchfield
    -0.52
    
    -0.52
    ystemet
    -0.52
    POSITIVE LOGITS
     wherefore
    0.55
     schuldig
    0.51
     AspNetCore
    0.50
     Wherefore
    0.49
     Slow
    0.48
    ThroughAttribute
    0.48
    НИК
    0.48
     <<<<<<<<<<<<<<
    0.46
    Slow
    0.45
     mulia
    0.45
    Activations Density 0.067%

    No Known Activations