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. 16-GEMMASCOPE-RES-16K
    6. 12460
    Prev
    Next
    INDEX
    Explanations

    API-related URL patterns and structural components in code

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

    Code snippets with URLs or API calls

    np_acts-logits-general · gemini-2.0-flash

    url paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.60
    UserDao
    -0.52
    ThroughAttribute
    -0.48
    br
    -0.48
     Yup
    -0.47
     Yep
    -0.47
     Yes
    -0.47
    CreateInfo
    -0.46
    
    -0.46
    Yes
    -0.45
    POSITIVE LOGITS
    :'/
    0.70
    الإنجليزية
    0.69
    ={`${
    0.64
    OGND
    0.62
    ölkerung
    0.60
     Italijanski
    0.60
    ftagPool
    0.59
    .*")]
    0.58
    ('/
    0.57
    บัติ
    0.57
    Activations Density 0.060%

    No Known Activations