© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1258
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of creature or organism, particularly related to the genus "creosote."

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

    starting with "cre" or "Cr"

    np_acts-logits-general · gemini-2.0-flash

    crepant resolutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Noto
    -0.57
     Luisa
    -0.56
    specifically
    -0.55
    :+:
    -0.55
    لينكات
    -0.55
     tartalomajánló
    -0.54
     Bergh
    -0.54
    WriteBarrier
    -0.54
    Enllaces
    -0.53
     Pelt
    -0.52
    POSITIVE LOGITS
     cre
    0.99
     Cre
    0.89
    Cre
    0.86
    cre
    0.78
     cré
    0.73
     CRE
    0.60
     CRED
    0.55
     crepe
    0.53
    qiang
    0.53
     OFDb
    0.51
    Activations Density 0.102%

    No Known Activations