© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7280
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, symbols, and notations within a document

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

    LaTeX mathematical equations and formatting in academic documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.90
     JpaRepository
    -0.88
    msgTypes
    -0.88
    featureID
    -0.88
    oredCriteria
    -0.87
    IsMutable
    -0.86
    parsedMessage
    -0.83
     gynhyrchwyd
    -0.83
     propOrder
    -0.83
     ExecuteAsync
    -0.82
    POSITIVE LOGITS
    displaystyle
    0.77
    $$\
    0.73
    $$
    0.63
    <code>
    0.52
    “
    0.50
    $
    0.48
    $\
    0.48
    <td>
    0.48
    <em>
    0.47
    \[
    0.46
    Activations Density 0.360%

    No Known Activations