© 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. 8947
    Prev
    Next
    INDEX
    Explanations

    technical keywords and identifiers related to programming and software development

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

    Code related to GPU drivers or complex numbers

    np_acts-logits-general · gemini-2.0-flash

    DRV function calls

    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
    SequentialGroup
    -0.81
     Chwiliwch
    -0.80
     تضيفلها
    -0.79
    DoubleQuotes
    -0.75
     ModelExpression
    -0.73
     surla
    -0.69
    ########.
    -0.68
    ValueStyle
    -0.66
    featureID
    -0.65
     jScrollPane
    -0.65
    POSITIVE LOGITS
     betweenstory
    0.50
    DataTo
    0.31
    SING
    0.28
     Boletín
    0.28
     однако
    0.28
    actéris
    0.27
     porém
    0.26
    (".",
    0.26
    OVERR
    0.25
    fions
    0.25
    Activations Density 1.521%

    No Known Activations