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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 612
    Prev
    Next
    INDEX
    Explanations

    probability-related terms and phrases in a statistical context

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

    Probability calculations

    np_acts-logits-general · gemini-2.0-flash

    picking probability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     distanciation
    -0.31
     entende
    -0.30
     almend
    -0.26
     corrid
    -0.26
     garçons
    -0.25
     rentrer
    -0.25
    scriptcase
    -0.25
     entendimiento
    -0.25
    readystatechange
    -0.24
     ویکی‌پدی
    -0.23
    POSITIVE LOGITS
     חיצוניים
    0.77
    [@BOS@]
    0.69
    <unused8>
    0.69
     パンチラ
    0.69
    <unused14>
    0.69
    <unused1>
    0.69
    <unused17>
    0.69
    <unused41>
    0.69
    <unused23>
    0.69
    <unused28>
    0.69
    Activations Density 0.286%

    No Known Activations