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. 5-GEMMASCOPE-RES-16K
    6. 4694
    Prev
    Next
    INDEX
    Explanations

    references to Wikipedia URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.76
    antMatchers
    -0.75
    WriteLiteral
    -0.70
    addCriterion
    -0.70
    TRAILING
    -0.65
     становника
    -0.64
    RectangleBorder
    -0.62
    帖最后由
    -0.62
    UnifiedTopology
    -0.61
    Issue
    -0.60
    POSITIVE LOGITS
    wikipedia
    2.56
     Wikipedia
    2.55
    Wikipedia
    2.32
     wikipedia
    2.10
    wiki
    2.00
    Wiki
    1.90
     wiki
    1.89
     Wiki
    1.88
     Wikipédia
    1.82
    wikimedia
    1.69
    Activations Density 0.093%

    No Known Activations