© 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. 10784
    Prev
    Next
    INDEX
    Explanations

    academic and scientific terminology related to biological processes and statistical concepts

    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
    แท
    -0.45
    dialogs
    -0.38
     deltag
    -0.37
     protokol
    -0.37
     Fortsch
    -0.36
    릎
    -0.36
    EndGlobalSection
    -0.36
    WithValue
    -0.36
    makeText
    -0.36
     sifat
    -0.35
    POSITIVE LOGITS
     diverting
    0.75
     Diver
    0.74
    Diver
    0.73
     diversion
    0.73
     diversions
    0.71
    EndContext
    0.66
    Convergence
    0.64
     ripping
    0.63
     divert
    0.63
     ri
    0.63
    Activations Density 1.121%

    No Known Activations