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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114063
    Prev
    Next
    INDEX
    Explanations

    structural elements or syntax in code

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

    mathematical notation or code constructs

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    RegressionTest
    -0.69
     ffilmiau
    -0.59
    archiviato
    -0.57
     disambiguazione
    -0.54
    tagHelperRunner
    -0.52
    invokeLater
    -0.49
    存于互联网档案馆
    -0.49
    AnimationsModule
    -0.48
     ویکی‌پدیای
    -0.48
    StoryboardSegue
    -0.47
    POSITIVE LOGITS
    rometers
    0.48
     Jove
    0.47
     conventions
    0.45
     Osiris
    0.44
    citenamefont
    0.44
    VersionUID
    0.43
     saints
    0.42
     sẻ
    0.42
    vron
    0.42
    langs
    0.42
    Activations Density 0.001%

    No Known Activations