© 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. 77780
    Prev
    Next
    INDEX
    Explanations

    the word "specifically" and similar terms indicating precision or focus

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

    specifying purpose or condition

    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
    存于互联网档案馆
    -0.64
     ſtate
    -0.50
     سای
    -0.49
     ſal
    -0.48
     suiv
    -0.47
     houſe
    -0.47
     inconn
    -0.46
     hjælp
    -0.46
    føl
    -0.46
     äta
    -0.45
    POSITIVE LOGITS
     particularly
    0.81
     primarily
    0.76
    marily
    0.75
     especially
    0.73
     specifically
    0.73
    sively
    0.72
    particularly
    0.72
    ticularly
    0.70
    ctively
    0.70
     predominantly
    0.69
    Activations Density 0.017%

    No Known Activations