© 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 EvalsExportsinterp-engineNEWAPI 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. 116146
    Prev
    Next
    INDEX
    Explanations

    legal terms and citations

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

    legislation and statutes

    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
    AccessorTable
    -0.57
    lgari
    -0.41
    complete
    -0.39
    undrum
    -0.38
     Etern
    -0.38
    kmale
    -0.37
     complete
    -0.37
    ttt
    -0.36
    miri
    -0.36
    stache
    -0.36
    POSITIVE LOGITS
     legislation
    0.60
    AnimationsModule
    0.54
     legislative
    0.54
     legisl
    0.54
     législation
    0.50
     StringTokenizer
    0.49
    WebServlet
    0.48
     legislature
    0.47
     lawmakers
    0.46
     leyes
    0.46
    Activations Density 0.019%

    No Known Activations