© 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. 3-GEMMASCOPE-RES-16K
    11. 4951
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods or instances

    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
     Normdatei
    -0.47
    godic
    -0.45
    IntoConstraints
    -0.44
     intelectual
    -0.41
     Alloy
    -0.39
    tujuan
    -0.38
     purpoſe
    -0.38
    äv
    -0.37
    IContainer
    -0.37
    hithe
    -0.37
    POSITIVE LOGITS
     times
    3.64
     Times
    3.06
    Times
    3.02
     TIMES
    3.00
    times
    2.59
    TIMES
    2.48
     Zeiten
    2.11
     tijden
    2.09
     veces
    1.85
     vezes
    1.80
    Activations Density 0.092%

    No Known Activations