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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 21853
    Prev
    Next
    INDEX
    Explanations

    references to code structure and control flow in programming

    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-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
    WithIOException
    -0.68
    richTextPanel
    -0.66
    UrlResolution
    -0.65
    transQ
    -0.65
    évaluateur
    -0.54
    setVerticalGroup
    -0.52
    :+:
    -0.51
    出版年
    -0.50
    LookAnd
    -0.49
    RegressionTest
    -0.48
    POSITIVE LOGITS
    gonic
    0.46
    ModelSerializer
    0.40
    AttributeSet
    0.38
    uwa
    0.36
    onner
    0.36
    Insee
    0.35
     käyt
    0.34
    pantalón
    0.34
    rigado
    0.34
     kollek
    0.34
    Activations Density 0.007%

    No Known Activations