© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 15112
    Prev
    Next
    INDEX
    Explanations

    elements related to touch screen calibration and menu item management in a programming context

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

    technical terms and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.96
     Infórmanos
    -0.82
     ainfi
    -0.77
     ſind
    -0.74
     ſont
    -0.72
     propOrder
    -0.70
     EconPapers
    -0.68
     plufieurs
    -0.68
     $_"
    -0.68
     dieſe
    -0.68
    POSITIVE LOGITS
    ();
    0.82
     (
    0.77
     =
    0.74
    .
    0.70
    ("
    0.67
    (
    0.66
    !
    0.64
    <eos>
    0.63
     ("
    0.59
     ();
    0.58
    Activations Density 0.221%

    No Known Activations