© 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. 72708
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating conditions, contrasts, or qualifiers in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    expandindo
    -0.63
     Administrativna
    -0.57
     disambiguazione
    -0.56
     препратки
    -0.56
    hyrchwyd
    -0.54
    webElementXpaths
    -0.51
    AISSEE
    -0.50
    новништво
    -0.50
     Infórmanos
    -0.49
    DockStyle
    -0.46
    POSITIVE LOGITS
    虽然
    0.70
    雖
    0.70
    though
    0.68
     zwar
    0.67
    雖然
    0.67
    虽
    0.66
    Though
    0.64
     although
    0.62
    虽说
    0.62
    although
    0.61
    Activations Density 0.210%

    No Known Activations