© 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. 23-GEMMASCOPE-RES-16K
    11. 12940
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values indicating counts or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.75
     defaultstate
    -0.70
     ivelany
    -0.69
    SharedDtor
    -0.69
    expandindo
    -0.68
     FetchType
    -0.67
    providedIn
    -0.66
     EnglishChoose
    -0.66
    הערות
    -0.66
    QMetaType
    -0.65
    POSITIVE LOGITS
    Newswire
    0.49
     posi
    0.43
    père
    0.42
     )
    0.42
    зво
    0.41
    bert
    0.41
    Scénario
    0.40
    KommentareTeilen
    0.40
    Tagged
    0.40
    زيل
    0.40
    Activations Density 0.145%

    No Known Activations