© 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. 15-GEMMASCOPE-RES-16K
    11. 5799
    Prev
    Next
    INDEX
    Explanations

    keywords related to activities and tasks involving creativity and learning

    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
     entire
    -0.48
    findpost
    -0.48
    WebElementEntity
    -0.46
     Verständ
    -0.41
     продъл
    -0.40
     ENTIRE
    -0.40
     AVAILABILITY
    -0.40
     PHOSPH
    -0.40
    xase
    -0.40
    WebpackPlugin
    -0.39
    POSITIVE LOGITS
     some
    0.80
     Some
    0.73
    Some
    0.72
    بعض
    0.71
     einige
    0.71
     некоторые
    0.70
    some
    0.69
    SOME
    0.68
     bazı
    0.66
     algunos
    0.65
    Activations Density 0.488%

    No Known Activations