© 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. 28-GEMMASCOPE-RES-16K
    11. 8062
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax used in coding languages

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

    Inside parenthesis or fractions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.46
    GIVEREF
    -0.43
    xrTableCell
    -0.39
    UIControlState
    -0.38
    postsleuth
    -0.37
    AMPLES
    -0.37
     Estadual
    -0.37
     textStatus
    -0.37
     vý
    -0.36
    mayr
    -0.36
    POSITIVE LOGITS
    ).\\
    0.54
    Билгалдахарш
    0.52
    endregion
    0.51
    ).
    0.50
    ...).
    0.49
    …).
    0.49
    ChrTalk
    0.48
    SequentialGroup
    0.48
    <h1>
    0.47
    )."
    0.46
    Activations Density 1.158%

    No Known Activations