© 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. 9816
    Prev
    Next
    INDEX
    Explanations

    elements related to technical or programming terminology

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

    quantities and formats

    np_acts-logits-general · gemini-2.5-flash-lite

    the first content token at the start of a sequence (the document-initial word).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    Tikang
    -0.61
    ########.
    -0.50
    ագրություններ
    -0.48
     صوتيه
    -0.48
    numerusform
    -0.46
     uska
    -0.45
    NECT
    -0.44
    MockBean
    -0.44
    optarg
    -0.43
    omock
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.51
    SaveChangesAsync
    0.51
     transférez
    0.48
    Хьажоргаш
    0.42
     otomatig
    0.40
     transfieras
    0.38
     Roskov
    0.37
    WillAppear
    0.37
    BeginInit
    0.37
    Personensuche
    0.36
    Activations Density 17.811%

    No Known Activations