© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 13692
    Prev
    Next
    INDEX
    Explanations

    code structure elements, particularly those involving function definitions and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.64
     informée
    -0.63
     queſta
    -0.63
    transQ
    -0.60
     Outputs
    -0.57
     outputs
    -0.56
    featureID
    -0.51
     Findings
    -0.50
     Outcomes
    -0.50
    __*/
    -0.49
    POSITIVE LOGITS
     result
    2.22
    result
    2.11
    Result
    1.40
     Result
    1.37
     RESULT
    1.33
     résultat
    1.28
    RESULT
    1.19
     resul
    1.12
     risultato
    1.10
     resultar
    1.09
    Activations Density 0.174%

    No Known Activations