© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 99528
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "push" in various contexts

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

    push to lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     للمعارف
    -0.66
    getValueAt
    -0.45
     \"%
    -0.44
     EconPapers
    -0.44
     "?
    -0.43
     lenker
    -0.43
     (\<
    -0.42
     "");
    -0.42
     \""
    -0.42
     '".$
    -0.42
    POSITIVE LOGITS
    push
    2.17
     push
    1.73
    Push
    1.61
     Push
    1.54
     PUSH
    1.43
    PUSH
    1.41
     pushing
    1.36
     pushed
    1.36
     pushes
    1.27
     Pushing
    1.23
    Activations Density 0.001%

    No Known Activations