© 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. 3725
    Prev
    Next
    INDEX
    Explanations

    references to information collection and user privacy

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

    Followed by "information," "owners," "accept," or "your."

    np_acts-logits-general · gemini-2.0-flash

    privacy policy terms and conditions

    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
     Chwiliwch
    -0.65
     kaarangay
    -0.64
     autorytatywna
    -0.63
    SourceChecksum
    -0.59
     estekak
    -0.57
     nahilalakip
    -0.55
    Chham
    -0.53
    AddTagHelper
    -0.53
    PyExc
    -0.53
     Exacts
    -0.52
    POSITIVE LOGITS
    ckså
    0.47
     område
    0.32
     ouver
    0.32
     Infór
    0.31
    htë
    0.31
     prêtres
    0.31
    hdessä
    0.31
     consommateurs
    0.30
     médec
    0.30
     kleid
    0.29
    Activations Density 0.132%

    No Known Activations