© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 194
    Prev
    Next
    INDEX
    Explanations

    references to clarity and understanding in a text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "clear"

    np_acts-logits-general · gemini-2.0-flash

    clear contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Վերցված
    -0.48
    ditionally
    -0.45
     adventures
    -0.43
    adventures
    -0.42
    onson
    -0.42
    tschafts
    -0.42
    Getenv
    -0.41
    multirow
    -0.41
     ADVENT
    -0.41
     дописавши
    -0.40
    POSITIVE LOGITS
     clear
    2.17
     Clear
    2.08
    Clear
    2.05
    clear
    2.03
     CLEAR
    1.81
    CLEAR
    1.71
     clears
    1.52
     clearer
    1.47
     clearness
    1.43
     clearest
    1.42
    Activations Density 0.173%

    No Known Activations