© 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. 12579
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to educational improvement and collaboration in specific fields

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

    preceding "should" or "to"

    np_acts-logits-general · gemini-2.0-flash

    actions and outcomes

    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
     surla
    -0.63
     propOrder
    -0.57
     unknownFields
    -0.53
     '{@
    -0.52
    UseVisualStyle
    -0.47
     EventArgs
    -0.47
     cref
    -0.46
    parsedMessage
    -0.46
    weile
    -0.45
     CanadaChoose
    -0.44
    POSITIVE LOGITS
     politika
    0.45
     policies
    0.42
     verdaderas
    0.41
     Majefty
    0.40
     should
    0.39
     politicians
    0.39
     verster
    0.38
     duide
    0.38
     nästa
    0.38
     sikre
    0.38
    Activations Density 0.292%

    No Known Activations