© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10646
    Prev
    Next
    INDEX
    Explanations

    objects and features related to security and access points in buildings or vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    windows, shades, and light transmission

    np_acts-logits-general · gemini-2.0-flash

    window and associated parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.54
    最快更新
    -0.53
    httphttps
    -0.50
     estekak
    -0.49
    fjspx
    -0.49
    StoryboardSegue
    -0.49
    AndEndTag
    -0.48
    новништво
    -0.47
     Signalez
    -0.47
     żyw
    -0.47
    POSITIVE LOGITS
     window
    0.75
     Window
    0.59
     windows
    0.57
    window
    0.55
    Window
    0.54
     glass
    0.50
    窗
    0.49
     Fenster
    0.47
    endpush
    0.46
     AssemblyCulture
    0.44
    Activations Density 0.250%

    No Known Activations