© 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. 6564
    Prev
    Next
    INDEX
    Explanations

    identifiers and values in data structures, particularly in programming contexts

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

    File paths with numbers

    np_acts-logits-general · gemini-2.0-flash

    file identifiers and GUIDs

    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
     propOrder
    -0.56
     crossorigin
    -0.49
    uxxxx
    -0.44
     AssemblyProduct
    -0.40
     revolved
    -0.38
    hely
    -0.38
    copyTo
    -0.38
    izh
    -0.37
    daq
    -0.36
     Spra
    -0.36
    POSITIVE LOGITS
    eqn
    0.60
    Diweddarwch
    0.54
     transfieras
    0.49
     Numerade
    0.48
     חיצוניים
    0.45
     EconPapers
    0.44
    Referencies
    0.42
    maßen
    0.42
    出版年
    0.42
     userSchema
    0.42
    Activations Density 0.017%

    No Known Activations