© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 773
    Prev
    Next
    INDEX
    Explanations

    references to names and their origins or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.83
    expandindo
    -0.74
     parson
    -0.72
    Hochspringen
    -0.70
     nakalista
    -0.70
     فريبيس
    -0.68
     estekak
    -0.67
     समीक्षाओं
    -0.66
    🏻‍♀️
    -0.65
     noDo
    -0.65
    POSITIVE LOGITS
     names
    0.72
     name
    0.69
    apimachinery
    0.66
     tag
    0.60
     NAME
    0.55
    omenclature
    0.54
     NAMES
    0.54
     Names
    0.51
    jsonwebtoken
    0.51
    names
    0.50
    Activations Density 0.174%

    No Known Activations