© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5296
    Prev
    Next
    INDEX
    Explanations

    references to personnel or workforce-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    gonic
    -0.52
     Nier
    -0.51
    goin
    -0.47
     OMIT
    -0.45
    come
    -0.44
    cure
    -0.42
    ondere
    -0.41
    gabriel
    -0.41
    :^(
    -0.41
     Schen
    -0.41
    POSITIVE LOGITS
     Staff
    1.55
     staff
    1.55
    Staff
    1.54
     STAFF
    1.34
    staff
    1.34
     staffs
    1.26
    STAFF
    1.25
     Staffing
    1.00
     staf
    1.00
     staffing
    0.95
    Activations Density 0.054%

    No Known Activations