© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 17653
    Prev
    Next
    INDEX
    Explanations

    references to types of wool and their qualities

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

    Wool and related materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorizaciones
    -0.54
     Autorisations
    -0.52
    localctx
    -0.52
    verwijspagina
    -0.48
    tabria
    -0.48
    fastjson
    -0.47
    ecirc
    -0.47
    醐
    -0.47
    LinkId
    -0.46
    gator
    -0.46
    POSITIVE LOGITS
     Wool
    1.09
     wool
    1.07
    Wool
    1.02
     Wo
    0.83
    Wo
    0.82
    wool
    0.82
     WO
    0.81
    WO
    0.76
     Woolf
    0.75
     woolen
    0.74
    Activations Density 0.005%

    No Known Activations