© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4547
    Prev
    Next
    INDEX
    Explanations

    specific code structures or syntax elements

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

    technical symbols and notation, like asterisks, percent signs, mathematical symbols, and programming-related tokens.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    -0.78
    webElementXpaths
    -0.75
     &___
    -0.74
    ArrowToggle
    -0.74
    NameInMap
    -0.71
    SharedDtor
    -0.69
    yntaxException
    -0.68
    verifyException
    -0.68
     Autorizaciones
    -0.68
     wireType
    -0.67
    POSITIVE LOGITS
     also
    0.44
    ditto
    0.39
     juga
    0.38
     additionally
    0.38
    Same
    0.38
     igualmente
    0.37
    same
    0.36
     Wassers
    0.36
     likewise
    0.35
     alternatively
    0.35
    Activations Density 1.127%

    No Known Activations