© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 82018
    Prev
    Next
    INDEX
    Explanations

    slashes at the beginning of lines or segments

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

    user input

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    liferay
    -0.44
     sahiptir
    -0.36
     vœ
    -0.33
     gé
    -0.32
     utom
    -0.32
     juſ
    -0.31
    kjø
    -0.30
     flavoured
    -0.30
    ミュ
    -0.30
     finnas
    -0.30
    POSITIVE LOGITS
    GEBURTSDATUM
    0.76
    OGND
    0.73
    httphttps
    0.69
     Chwiliwch
    0.68
     насељу
    0.65
    makeConstraints
    0.65
    Халык
    0.65
    WriteTagHelper
    0.64
     autorytatywna
    0.63
    AppMethodBeat
    0.61
    Activations Density 0.000%

    No Known Activations