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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12531
    Prev
    Next
    INDEX
    Explanations

    elements related to programming functions and definitions

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

    Python type hints and annotations

    np_acts-logits-general · gemini-2.0-flash

    Python type hints and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FromNib
    -0.30
    InitVars
    -0.29
     duplicates
    -0.28
     travel
    -0.28
    放在
    -0.28
     invalid
    -0.28
     bait
    -0.28
     Hag
    -0.27
     parecer
    -0.27
    続きを読む
    -0.27
    POSITIVE LOGITS
    setVerticalGroup
    0.78
    TagMode
    0.66
    AndEndTag
    0.62
     str
    0.62
    tagHelperRunner
    0.61
    str
    0.61
    strate
    0.59
    strates
    0.58
    aarrggbb
    0.58
    Union
    0.56
    Activations Density 0.162%

    No Known Activations