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. 12228
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms related to thresholds and limits

    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
    ########.
    -0.66
    abestanden
    -0.64
    
    -0.57
     CWE
    -0.54
    CWE
    -0.52
    httphttps
    -0.49
    ритори
    -0.48
    CGRectMake
    -0.48
    TintMode
    -0.48
    isle
    -0.48
    POSITIVE LOGITS
     what
    0.80
     maximum
    0.76
    twice
    0.73
     twice
    0.72
     theoretical
    0.72
     sum
    0.69
     maksimum
    0.68
    maximum
    0.68
     standard
    0.68
     fédé
    0.66
    Activations Density 0.756%

    No Known Activations