© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 420
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "const" in code

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

    Code snippets with "const" keyword

    np_acts-logits-general · gemini-2.0-flash

    declaring constants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    存于互联网档案馆
    -0.66
     wireType
    -0.66
    nologue
    -0.56
     Gelen
    -0.56
     Mejía
    -0.56
    WebServlet
    -0.54
     marginLeft
    -0.54
    marginLeft
    -0.54
    GEBURTS
    -0.54
     Hügel
    -0.53
    POSITIVE LOGITS
    const
    1.26
     const
    1.03
    Const
    0.79
     Const
    0.77
     Constan
    0.65
    CONST
    0.63
     Constant
    0.62
     Constable
    0.61
     constriction
    0.59
     CONSTANT
    0.57
    Activations Density 0.104%

    No Known Activations