© 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. 10551
    Prev
    Next
    INDEX
    Explanations

    technical specifications and references related to scientific research

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

    Section numbers (e.g., 2.1, 4.2)

    np_acts-logits-general · gemini-2.0-flash

    section references with numbers

    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
     JpaRepository
    -0.58
    onOptions
    -0.56
     invokingState
    -0.52
     linkovi
    -0.51
    TagMode
    -0.51
    KURZBESCHREIBUNG
    -0.50
    SaveVideo
    -0.50
    Bakgrunnsstoff
    -0.50
    onViewCreated
    -0.50
     queſta
    -0.48
    POSITIVE LOGITS
    GOTREF
    0.43
    hyp
    0.37
    rogen
    0.37
    KeySpec
    0.36
    (!
    0.36
    unya
    0.35
    Zeneca
    0.35
    !
    0.35
     屋根
    0.35
    !)
    0.34
    Activations Density 1.357%

    No Known Activations