© 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. 15-GEMMASCOPE-RES-16K
    11. 3596
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential actions or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Estat
    -0.37
     Gor
    -0.32
    ジック
    -0.31
     measuring
    -0.31
     centered
    -0.30
     premiers
    -0.30
     Arca
    -0.30
     computing
    -0.28
     again
    -0.28
     Obec
    -0.28
    POSITIVE LOGITS
     možné
    0.76
     ممکن
    0.75
     potentially
    0.74
    potentially
    0.73
     akár
    0.73
     boleh
    0.68
     pouvant
    0.68
    possible
    0.66
     possible
    0.66
    Possible
    0.66
    Activations Density 0.645%

    No Known Activations