© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 121950
    Prev
    Next
    INDEX
    Explanations

    terminology related to billiards and cue sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     AssemblyTitle
    -0.56
     XCTest
    -0.55
     Audiodateien
    -0.51
    degard
    -0.49
     MonoBehaviour
    -0.48
    OGND
    -0.48
    dbury
    -0.46
     webdriver
    -0.46
    WEBPACK
    -0.45
    зулта
    -0.45
    POSITIVE LOGITS
     billiard
    0.82
     billi
    0.66
     Billi
    0.56
    ooker
    0.54
    🎱
    0.54
     beer
    0.49
     liquor
    0.48
     poker
    0.47
     whiskey
    0.45
    LookAnd
    0.45
    Activations Density 0.003%

    No Known Activations