© 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. 3-GEMMASCOPE-RES-16K
    11. 15635
    Prev
    Next
    INDEX
    Explanations

    descriptions of significant sporting events and actions related to scoring or gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.38
    共
    -0.37
    log
    -0.36
    enschappelijke
    -0.34
     pegatinas
    -0.33
     boyunca
    -0.33
     contento
    -0.32
    (-
    -0.32
    気を
    -0.32
    -
    -0.32
    POSITIVE LOGITS
    __*/
    0.99
    writeFieldEnd
    0.95
    principalColumn
    0.89
    
    0.84
    mappedBy
    0.81
    transQ
    0.80
    IsContent
    0.79
    httphttps
    0.78
    */].
    0.77
     numberOfRows
    0.77
    Activations Density 0.316%

    No Known Activations