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. 6697
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific event or action represented by significant legal or formal proceedings

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

    Preceding certain punctuation or section breaks

    np_acts-logits-general · gemini-2.0-flash

    reading continuation

    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
    цездатний
    -0.92
     EClass
    -0.84
     CWE
    -0.81
    رشف
    -0.79
    setVerticalGroup
    -0.78
    mergeFrom
    -0.78
    ⟬
    -0.77
    tanleria
    -0.77
    yntaxException
    -0.76
    Vidite
    -0.75
    POSITIVE LOGITS
    <eos>
    0.86
    ↵↵
    0.57
    Clik
    0.52
    
    0.47
    неопр
    0.47
     برانيه
    0.46
     View
    0.45
    HttpRequest
    0.45
    </em>
    0.45
    DebuggerStep
    0.44
    Activations Density 0.083%

    No Known Activations