© 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. 7066
    Prev
    Next
    INDEX
    Explanations

    references to channels and their related characteristics or components in various contexts

    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
    nezeu
    -0.34
     tiap
    -0.32
     uș
    -0.31
     seconds
    -0.30
    rstrip
    -0.30
     gyhoeddwyd
    -0.30
    SPATH
    -0.30
    horizontalLayout
    -0.29
    ighbor
    -0.28
    ごと
    -0.28
    POSITIVE LOGITS
    Multiline
    0.56
     bezeichneter
    0.55
    ChildScrollView
    0.54
    ToScroll
    0.52
    gridx
    0.51
     Roskov
    0.50
    RunWith
    0.48
    istocene
    0.48
    Controllo
    0.47
    InjectAttribute
    0.46
    Activations Density 1.367%

    No Known Activations