© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13347
    Prev
    Next
    INDEX
    Explanations

    phrases related to user interactions and error messages in software applications

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

    Following certain foreign words

    np_acts-logits-general · gemini-2.0-flash

    sort order

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    pperware
    -0.40
    OVERR
    -0.37
    se
    -0.36
    ņš
    -0.35
    évaluateur
    -0.34
    field
    -0.33
    ambilan
    -0.33
    󠁴
    -0.32
    el
    -0.32
    3
    -0.32
    POSITIVE LOGITS
     XNUMX
    0.68
     ſans
    0.63
     propOrder
    0.63
    BibitemShut
    0.60
    <unused23>
    0.57
    <unused14>
    0.57
    <unused28>
    0.57
    <unused43>
    0.57
    [@BOS@]
    0.57
    <unused1>
    0.57
    Activations Density 0.150%

    No Known Activations