© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9800
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "that" in various contexts, especially in legal or formal documentation

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

    Text within parentheses, often enumerated

    np_acts-logits-general · gemini-2.0-flash

    Roman numerals for listing

    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
    sizeCache
    -0.91
     незавершена
    -0.85
    adaptiveStyles
    -0.85
     فريبيس
    -0.83
    abestanden
    -0.81
    addCriterion
    -0.79
    InjectAttribute
    -0.78
    enterOuterAlt
    -0.78
    oneofs
    -0.76
    providedIn
    -0.75
    POSITIVE LOGITS
    ii
    0.74
    iii
    0.70
    vii
    0.60
    vi
    0.60
    iv
    0.54
    viii
    0.48
    iiii
    0.48
    xii
    0.48
    ङ
    0.47
    i
    0.46
    Activations Density 0.186%

    No Known Activations