© 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. 20-GEMMASCOPE-RES-131K
    11. 65571
    Prev
    Next
    INDEX
    Explanations

    terms related to crates and craters

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

    crate, crater, creatine

    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
    KommentareTeilen
    -0.52
    illips
    -0.51
    inherits
    -0.51
     ppp
    -0.51
     Nippon
    -0.49
     PIB
    -0.49
     Վերցված
    -0.49
     NIS
    -0.49
     삼
    -0.49
    ⓘ
    -0.48
    POSITIVE LOGITS
     Crate
    1.13
     crate
    1.12
     crates
    0.92
    crate
    0.85
     Crater
    0.69
     crater
    0.66
     crat
    0.57
     createSprite
    0.55
     Caja
    0.54
    CONTAINER
    0.53
    Activations Density 0.003%

    No Known Activations