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. 9-GEMMASCOPE-RES-131K
    6. 81865
    Prev
    Next
    INDEX
    Explanations

    pieces of syntax and function definitions in programming code

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

    function calls or conversions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.56
    NameInMap
    -0.54
     ब्रेकडाउन
    -0.53
     StatefulWidget
    -0.52
     Infórmanos
    -0.51
    点此举报
    -0.50
    AsUp
    -0.48
    LabelTagHelper
    -0.47
     GenerationType
    -0.47
     snippetHide
    -0.47
    POSITIVE LOGITS
     conversion
    0.61
     transformation
    0.57
     transforming
    0.56
     converting
    0.56
    cvtColor
    0.54
     Converting
    0.52
    Converter
    0.51
     NSCoder
    0.50
    Atoi
    0.50
    変換
    0.49
    Activations Density 0.168%

    No Known Activations