© 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. 10786
    Prev
    Next
    INDEX
    Explanations

    code-specific syntax and structures related to programming tasks

    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
    ViewImports
    -0.83
    parsedMessage
    -0.81
    -------------</
    -0.71
    GEBURTSDATUM
    -0.68
    UserScript
    -0.64
    OGND
    -0.63
    TagMode
    -0.61
     виправивши
    -0.60
     الرياضيه
    -0.59
     queſta
    -0.59
    POSITIVE LOGITS
     finally
    0.63
    Final
    0.63
     final
    0.62
     Final
    0.60
     FINAL
    0.58
    FINAL
    0.56
    final
    0.55
     FINALLY
    0.53
     finalizar
    0.53
     Finally
    0.51
    Activations Density 0.517%

    No Known Activations