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. 20-GEMMASCOPE-RES-16K
    6. 9707
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "per" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     AssemblyCulture
    -0.62
    modb
    -0.61
    centration
    -0.57
    wright
    -0.56
    pement
    -0.56
    GEBURTSDATUM
    -0.55
    timbangan
    -0.54
    SplashScreen
    -0.53
    keits
    -0.53
    ‌شده
    -0.52
    POSITIVE LOGITS
    ArgsConstructor
    0.63
    per
    0.61
    awtextra
    0.60
     capita
    0.56
     per
    0.56
    AddTagHelper
    0.51
     cent
    0.51
     transfieras
    0.50
    canestro
    0.47
    ⓧ
    0.47
    Activations Density 0.057%

    No Known Activations