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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 8703
    Prev
    Next
    INDEX
    Explanations

    technical claims and descriptions related to semiconductor devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    out
    -0.48
    once
    -0.47
    <code>
    -0.46
     bef
    -0.46
    beta
    -0.45
    zul
    -0.45
    alpha
    -0.44
    дке
    -0.44
    rov
    -0.43
    caj
    -0.43
    POSITIVE LOGITS
     kasarigan
    1.09
    GEBURTSDATUM
    1.08
    rungsseite
    0.90
     kaarangay
    0.76
    nemia
    0.75
    !*\
    0.74
    PMailer
    0.73
     }}$}
    0.73
    saurus
    0.73
    abestanden
    0.71
    Activations Density 0.181%

    No Known Activations