© 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. 6722
    Prev
    Next
    INDEX
    Explanations

    programming structures and functions related to data handling and manipulation

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

    programming-related tokens and operations, especially around creating and manipulating data structures and variables.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    code-related mentions of outputs/return values—especially initializing or assigning a result and setting up writing output (e.g., files or return values)

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    variable assignments and initializations in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    bcryptjs
    -0.43
    
    -0.39
    CppCodeGen
    -0.36
    pat
    -0.35
    MessageTagHelper
    -0.34
    setTimeout
    -0.33
    setPointSize
    -0.32
     setTimeout
    -0.32
     Pat
    -0.32
     Forst
    -0.31
    POSITIVE LOGITS
    IsMutable
    0.70
    WithIOException
    0.61
    IGraphics
    0.58
    новништво
    0.58
    httphttps
    0.57
    Diweddarwch
    0.56
    ">//
    0.52
    dafx
    0.52
     وتسجيلات
    0.49
    はじめに
    0.48
    Activations Density 0.147%

    No Known Activations