© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11566
    Prev
    Next
    INDEX
    Explanations

    the presence of actions or commands related to performing tasks or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CreateMap
    -0.59
    featureID
    -0.54
     ✭✭
    -0.54
    setof
    -0.51
     Lipa
    -0.49
    VIAF
    -0.49
    httphttps
    -0.48
    Становништво
    -0.48
    FieldBuilder
    -0.48
     PTA
    -0.47
    POSITIVE LOGITS
     doing
    0.56
    Doing
    0.54
     acest
    0.54
    doing
    0.52
     DOING
    0.47
    autaire
    0.47
     Doing
    0.46
     spéciaux
    0.41
     lucru
    0.41
     suerte
    0.41
    Activations Density 0.360%

    No Known Activations