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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15828
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    addCriterion
    -0.70
    
    -0.69
    Jeografia
    -0.65
    dafx
    -0.63
    WebVitals
    -0.60
    minecraftforge
    -0.58
    encodeWith
    -0.57
     հղումներ
    -0.57
    ỡng
    -0.56
     estekak
    -0.54
    POSITIVE LOGITS
    <sup>
    0.43
    <i>
    0.42
    <u>
    0.39
    <em>
    0.39
    <sub>
    0.39
    rungsseite
    0.39
    <strong>
    0.38
    tfrac
    0.36
    évaluateur
    0.36
    <s>
    0.35
    Activations Density 0.710%

    No Known Activations