© 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. 23-GEMMASCOPE-RES-16K
    11. 3953
    Prev
    Next
    INDEX
    Explanations

    structured data handling, focusing on return statements and identifiers in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⟬
    -0.57
     transférez
    -0.53
    bootstrapcdn
    -0.51
    TagMode
    -0.50
     astore
    -0.49
    migrationBuilder
    -0.48
     CURIAM
    -0.48
     gewöhnlich
    -0.46
    +#+#
    -0.45
    IntoConstraints
    -0.44
    POSITIVE LOGITS
     utafitiHapana
    0.47
     للاسماء
    0.44
    hyrchwyd
    0.37
    Xr
    0.36
     "..\..\..\
    0.35
     please
    0.34
    的样子
    0.34
    ьажоргаш
    0.34
     estekak
    0.34
     Please
    0.33
    Activations Density 0.328%

    No Known Activations