© 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. 13765
    Prev
    Next
    INDEX
    Explanations

    names of individuals, political figures, and organizations

    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
     autorytatywna
    -0.73
    modelBuilder
    -0.66
    IsMutable
    -0.63
    fjspx
    -0.62
    HasAnnotation
    -0.58
    Autoritní
    -0.58
     Ghat
    -0.57
    UAGES
    -0.56
    anyard
    -0.55
    tilage
    -0.54
    POSITIVE LOGITS
     alias
    0.77
    SuppressLint
    0.58
     noqa
    0.54
     Abonnez
    0.49
    autoconfigure
    0.49
     OnInit
    0.47
    KommentareTeilen
    0.46
    setPref
    0.45
     NSCoder
    0.44
    +#+
    0.44
    Activations Density 0.136%

    No Known Activations