© 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. 14736
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and their citations

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

    Capital letters followed by punctuation or mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    [C]{}haracterizations

    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
    IntoConstraints
    -0.97
    rungsseite
    -0.93
    Personendaten
    -0.88
     ujednoznacz
    -0.78
    IsMutable
    -0.76
     estekak
    -0.75
     CanadaChoose
    -0.75
    Архівовано
    -0.75
    󠁿
    -0.74
    TagMode
    -0.72
    POSITIVE LOGITS
     nahilalakip
    0.29
     polie
    0.27
     intervi
    0.25
    SysUser
    0.22
     kuh
    0.21
     nieder
    0.20
    manns
    0.20
    MatInputModule
    0.20
    ["
    0.20
    ⣿⣿
    0.20
    Activations Density 1.386%

    No Known Activations