© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11040
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those in the range of thirty to sixty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EClass
    -0.41
    ︎
    -0.39
    windowFixed
    -0.38
    phosa
    -0.34
     '\\;'
    -0.34
    MathML
    -0.33
     susi
    -0.33
    eraard
    -0.32
    ifs
    -0.32
     ביותר
    -0.31
    POSITIVE LOGITS
     thirty
    2.58
     forty
    2.56
     fifty
    2.50
     sixty
    2.48
     twenty
    2.47
     seventy
    2.42
     eighty
    2.41
     ninety
    2.23
    twenty
    2.22
     Thirty
    2.20
    Activations Density 0.078%

    No Known Activations