© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3508
    Prev
    Next
    INDEX
    Explanations

    the word "found" indicating discovery or realization

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

    Follows "found" or "would"

    np_acts-logits-general · gemini-2.0-flash

    found or would followed by a word

    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
    ConstraintMaker
    -0.54
    pecabe
    -0.50
    verwijspagina
    -0.47
     maș
    -0.44
     estekak
    -0.43
    المناصب
    -0.40
     ostavi
    -0.37
     Lozano
    -0.37
    Ligações
    -0.36
    تقاوى
    -0.36
    POSITIVE LOGITS
    aleg
    0.56
     Argos
    0.53
     archi
    0.52
    Tess
    0.52
     considere
    0.51
     Eyre
    0.50
     стре
    0.49
    ✷
    0.49
    dre
    0.49
     utili
    0.48
    Activations Density 0.690%

    No Known Activations