© 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. 9-GEMMASCOPE-RES-16K
    11. 7873
    Prev
    Next
    INDEX
    Explanations

    terms related to maintenance and care of mechanical or physical systems

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

    technical terms related to surface materials, textures, and abrasive processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    —
    -0.32
     entirely
    -0.30
     drept
    -0.30
     instalação
    -0.30
     capucha
    -0.29
    fastjson
    -0.29
     imaginación
    -0.29
    nav
    -0.29
    ViewInit
    -0.28
     NSCoder
    -0.27
    POSITIVE LOGITS
    tagHelperRunner
    0.77
     AssemblyCulture
    0.77
     abrasive
    0.72
     sandpaper
    0.67
    setVerticalGroup
    0.67
    oa̍t
    0.61
     polishing
    0.59
     utafitiHapana
    0.59
    VIAF
    0.59
     Signalez
    0.58
    Activations Density 0.242%

    No Known Activations