Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56100
    Prev
    Next
    INDEX
    Explanations

    references to tools related to cutting or shearing

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

    shear strain, rate, stress

    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
     ActivatedRoute
    -0.53
     ftate
    -0.48
    forName
    -0.48
     informée
    -0.45
     East
    -0.45
    tvguidetime
    -0.44
    onAttach
    -0.44
     Oce
    -0.44
     Level
    -0.43
     Santa
    -0.43
    POSITIVE LOGITS
     Scissors
    1.20
    Scissors
    1.13
     scissors
    1.13
    scissors
    1.02
     scissor
    0.92
    issor
    0.86
     pliers
    0.68
    issors
    0.60
     forceps
    0.57
     shears
    0.52
    Activations Density 0.011%

    No Known Activations