© 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. 3362
    Prev
    Next
    INDEX
    Explanations

    Android XML layout attributes and configurations

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

    Code or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    closing brace, semicolon, or percent

    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
    RenderAtEndOf
    -1.00
    AndEndTag
    -0.93
     مرئيه
    -0.92
    $_['
    -0.91
     ModelExpression
    -0.90
    ロウィン
    -0.85
    UnusedPrivate
    -0.85
    addCriterion
    -0.85
    ########.
    -0.83
    featureID
    -0.81
    POSITIVE LOGITS
    ↵
    0.52
     verz
    0.43
    <eos>
    0.40
    ↵↵
    0.35
    and
    0.32
    Repeti
    0.31
     ск
    0.31
    .
    0.31
     перво
    0.30
     After
    0.30
    Activations Density 0.171%

    No Known Activations