© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 4707
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and specifications, particularly related to distances and areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEE
    -0.40
    IntoConstraints
    -0.35
    RSpec
    -0.35
     bija
    -0.35
    WebElementEntity
    -0.35
    getDoctrine
    -0.34
    tgär
    -0.34
    vats
    -0.33
    rawDesc
    -0.33
    itzer
    -0.32
    POSITIVE LOGITS
     miles
    2.20
     mile
    1.96
     km
    1.90
     kilometers
    1.78
    miles
    1.76
    km
    1.75
     kilometres
    1.75
     kilometer
    1.68
    mile
    1.63
     MILES
    1.63
    Activations Density 0.299%

    No Known Activations