© 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. 219
    Prev
    Next
    INDEX
    Explanations

    terms related to anterior cruciate ligament (ACL) injuries and their risk factors

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

    joint injuries and medical procedures

    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
    HostException
    -0.36
    oneofs
    -0.35
    pulumi
    -0.31
    awtextra
    -0.30
     utafitiHapana
    -0.30
     typo
    -0.29
    Tikang
    -0.29
    Hentet
    -0.28
     subido
    -0.28
    Overnight
    -0.27
    POSITIVE LOGITS
    riceps
    0.63
     ligament
    0.60
    icitis
    0.59
     ligaments
    0.58
     surla
    0.57
    存于互联网档案馆
    0.57
     Knee
    0.56
     cedera
    0.53
    Knee
    0.53
     knee
    0.53
    Activations Density 0.046%

    No Known Activations