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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 52561
    Prev
    Next
    INDEX
    Explanations

    function definitions and their parameters in programming code

    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
     expansión
    -0.43
    RotationOrder
    -0.43
     expansion
    -0.42
     getItemCount
    -0.38
    Empereur
    -0.38
    DispatchQueue
    -0.38
     <=",
    -0.38
     expansions
    -0.38
     Chwiliwch
    -0.37
    TemporalType
    -0.37
    POSITIVE LOGITS
    ArgsConstructor
    0.71
    脚注の使い方
    0.67
    transQ
    0.65
     CURIAM
    0.48
    richTextPanel
    0.47
    fjspx
    0.45
    ValueGenerated
    0.42
    DeleteBehavior
    0.42
    setVerticalGroup
    0.41
    ModelForm
    0.40
    Activations Density 0.003%

    No Known Activations