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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14938
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, particularly interfaces and their properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.35
    翻攝
    -0.33
     pro
    -0.33
     n
    -0.33
     ur
    -0.32
     Til
    -0.32
     
    -0.32
    wohner
    -0.31
     String
    -0.31
    ins
    -0.29
    POSITIVE LOGITS
     EconPapers
    0.72
     IERC
    0.71
    OGND
    0.71
     interface
    0.66
    Personensuche
    0.65
    .*")]
    0.63
    interface
    0.62
    parsedMessage
    0.62
     interfaces
    0.62
    inheritDoc
    0.62
    Activations Density 0.351%

    No Known Activations