© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 3703
    Prev
    Next
    INDEX
    Explanations

    references to sports matches and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.60
    ectoria
    -0.57
     tami
    -0.56
    asantry
    -0.51
    )++;
    -0.50
    ecraft
    -0.50
    WebMethod
    -0.49
    //
    -0.49
     CanadaChoose
    -0.49
     Monfieur
    -0.48
    POSITIVE LOGITS
     mxArray
    0.72
     finals
    0.64
     finalist
    0.64
     finalists
    0.63
    決勝
    0.57
     Finals
    0.56
     NUKAT
    0.55
     final
    0.53
    Finals
    0.51
    Semif
    0.51
    Activations Density 0.246%

    No Known Activations