Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 13980
    Prev
    Next
    INDEX
    Explanations

    references to scientific or medical analysis processes

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

    Preceding percentages, parentheses, or certain function words

    np_acts-logits-general · gemini-2.0-flash

    automatic analyzers, formaldehyde, latex, license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.64
     beginnetje
    -0.63
    MENAFN
    -0.63
     שוליים
    -0.61
    doGet
    -0.57
    GEBURTSDATUM
    -0.57
    setVerticalGroup
    -0.56
    providedIn
    -0.56
    AccessFile
    -0.54
     Quince
    -0.54
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵
    0.64
     resourceCulture
    0.56
    ↵↵↵↵↵↵
    0.54
    </code>
    0.49
    ↵↵↵↵↵
    0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    Activations Density 0.127%

    No Known Activations