© 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. 38-GEMMASCOPE-RES-16K
    11. 12370
    Prev
    Next
    INDEX
    Explanations

    HTML code structure related to links and stylesheets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.47
     للاسماء
    -0.44
    chè
    -0.42
    ɵɵelementStart
    -0.40
    +#+#
    -0.39
     condividere
    -0.38
     binary
    -0.37
    msgTypes
    -0.37
    cipar
    -0.37
    Derbyniad
    -0.37
    POSITIVE LOGITS
    stylesheet
    0.49
    manifest
    0.48
    alternate
    0.47
     المعيارى
    0.44
     alternate
    0.43
     typelib
    0.42
    apple
    0.42
    PositiveButton
    0.41
     folha
    0.40
     DEFENSE
    0.39
    Activations Density 0.638%

    No Known Activations