© 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. 12578
    Prev
    Next
    INDEX
    Explanations

    links to online resources and information about events and presentations

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

    Links or data sources

    np_acts-logits-general · gemini-2.0-flash

    website addresses or downloads

    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
    Personendaten
    -0.40
    THISDAY
    -0.38
    SuspendLayout
    -0.37
    辞典
    -0.36
    Sides
    -0.35
    Gründe
    -0.34
     PCS
    -0.33
    arrol
    -0.33
     GenerationType
    -0.33
     Lua
    -0.32
    POSITIVE LOGITS
     downloads
    0.60
     download
    0.57
    downloads
    0.56
     downloadable
    0.54
     downloading
    0.52
    Bakgrunnsstoff
    0.51
    download
    0.50
     Administrativna
    0.49
    Downloads
    0.49
     protoimpl
    0.48
    Activations Density 0.235%

    No Known Activations