© 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. 33-GEMMASCOPE-RES-16K
    11. 12517
    Prev
    Next
    INDEX
    Explanations

    text that discusses grouping or categorization into multiple sections or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.60
    AnchorStyles
    -0.58
    beelden
    -0.53
     resourceCulture
    -0.46
    Parcelize
    -0.44
    kje
    -0.44
     שוליים
    -0.43
    rungsseite
    -0.43
    itemBuilder
    -0.42
    CELLANEOUS
    -0.41
    POSITIVE LOGITS
     sub
    0.81
     clusters
    0.80
     subsections
    0.77
     distinct
    0.75
     groupings
    0.75
     blocks
    0.75
     groups
    0.74
     sections
    0.71
     subgroups
    0.68
     divisions
    0.65
    Activations Density 1.176%

    No Known Activations