© 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. 3727
    Prev
    Next
    INDEX
    Explanations

    comparative language relating to performance and quality

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

    Tokens followed by comparative words

    np_acts-logits-general · gemini-2.0-flash

    comparative scale

    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
    مد
    -0.35
     مد
    -0.31
    base
    -0.31
     base
    -0.30
     matter
    -0.29
    ump
    -0.29
     outside
    -0.28
    ang
    -0.28
    xy
    -0.27
     Martin
    -0.27
    POSITIVE LOGITS
    RegressionTest
    0.84
     صوتيه
    0.77
     autorytatywna
    0.75
     MainAxisSize
    0.74
     Италијани
    0.73
    SharedDtor
    0.72
     للاسماء
    0.69
    Personendaten
    0.68
    rungsseite
    0.67
    +#+#
    0.66
    Activations Density 0.599%

    No Known Activations