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

    Neuronpedia

    Jacobian LensNEW
    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. 10177
    Prev
    Next
    INDEX
    Explanations

    elements of code and programming syntax used in functions

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

    Code, often with parentheses and brackets

    np_acts-logits-general · gemini-2.0-flash

    code blocks and math formulas

    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
     odst
    -0.39
    ↵↵
    -0.38
    aler
    -0.38
    ulu
    -0.37
    gu
    -0.36
    imageio
    -0.36
     Joshua
    -0.35
    <eos>
    -0.35
    moid
    -0.35
    uestamente
    -0.35
    POSITIVE LOGITS
     defaultstate
    0.61
    DIPSETTING
    0.57
     Normdatei
    0.57
    Personensuche
    0.57
    prepareStatement
    0.57
    matchCondition
    0.57
    ########.
    0.56
    CloseOperation
    0.56
    yntaxException
    0.54
    AnchorStyles
    0.54
    Activations Density 1.058%

    No Known Activations