© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4583
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements or definitions in a code-like structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
     '\\;'
    -0.77
    AndEndTag
    -0.70
     unknownFields
    -0.69
     estekak
    -0.68
    webElementXpaths
    -0.65
    TintMode
    -0.63
     الرياضيه
    -0.63
    withIdentifier
    -0.62
    StructEnd
    -0.60
    (!__
    -0.60
    POSITIVE LOGITS
    LOAT
    0.52
     sở
    0.45
    ⎩
    0.44
    iqué
    0.44
    arpur
    0.43
     kaf
    0.43
    äch
    0.42
    LLAB
    0.42
     khiển
    0.41
    pannt
    0.41
    Activations Density 0.656%

    No Known Activations