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. 5-GEMMASCOPE-RES-16K
    6. 13146
    Prev
    Next
    INDEX
    Explanations

    the word "only" and related expressions indicating exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.82
    $($
    -0.69
     Verdi
    -0.68
     zah
    -0.66
    िल्म
    -0.65
     Falcons
    -0.64
     cardiovascular
    -0.63
     AssemblyCulture
    -0.62
     Davenport
    -0.62
    falen
    -0.62
    POSITIVE LOGITS
     only
    2.02
     Only
    1.78
    only
    1.70
    Only
    1.70
    ONLY
    1.67
     ONLY
    1.64
     seulement
    1.39
    Sólo
    1.33
     лишь
    1.31
    nly
    1.24
    Activations Density 0.122%

    No Known Activations