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. 10024
    Prev
    Next
    INDEX
    Explanations

    phrases indicating thorough or extensive evaluations and analyses

    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
    roep
    -0.52
     Inversion
    -0.50
     okol
    -0.49
    空き
    -0.48
     Feliz
    -0.47
    tfrac
    -0.47
     Trick
    -0.46
     למש
    -0.46
    Predict
    -0.46
     Noc
    -0.46
    POSITIVE LOGITS
     comprehensive
    2.04
    Comprehensive
    1.88
    comprehensive
    1.85
     thorough
    1.82
     Comprehensive
    1.79
    prehensive
    1.73
     extensive
    1.65
    Extensive
    1.61
    extensive
    1.60
     Extensive
    1.57
    Activations Density 0.199%

    No Known Activations