Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6399
    Prev
    Next
    INDEX
    Explanations

    references to vintage items or concepts related to nostalgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.78
    WriteAttribute
    -0.72
    Kama
    -0.72
     Hag
    -0.70
    opheles
    -0.69
     Kama
    -0.66
    +#+#
    -0.66
     Verstappen
    -0.65
    Hauptartikel
    -0.65
    ѓ
    -0.65
    POSITIVE LOGITS
     vintage
    1.23
    vintage
    1.22
    vin
    1.11
     vin
    1.09
     Vintage
    1.05
    Vintage
    1.03
     Vin
    1.03
    Vin
    0.97
    INTAGE
    0.90
     tender
    0.83
    Activations Density 0.076%

    No Known Activations