© 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. 66678
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and" in the text

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

    and will

    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
    RenderAtEndOf
    -0.84
    Rujuakan
    -0.71
     zwiſchen
    -0.71
     pinulongan
    -0.70
     deſſen
    -0.68
    <unused41>
    -0.68
    <unused68>
    -0.68
    <unused23>
    -0.68
    <unused74>
    -0.68
    <pad>
    -0.68
    POSITIVE LOGITS
     I
    0.48
     hence
    0.48
     it
    0.47
     we
    0.47
     but
    0.46
    I
    0.46
    but
    0.44
     which
    0.44
     is
    0.43
    而
    0.42
    Activations Density 0.277%

    No Known Activations