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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4656
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of 'this'

    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
    .
    -0.55
     scolaires
    -0.52
    ,
    -0.46
     and
    -0.45
     Maintenant
    -0.39
    。
    -0.39
     egip
    -0.34
     demain
    -0.33
     électroniques
    -0.33
     buka
    -0.33
    POSITIVE LOGITS
    AsUp
    1.20
     שוליים
    1.15
    GOTREF
    1.09
     kaynağından
    1.02
    }{*}{
    1.01
     MainAxisSize
    1.01
     فريبيس
    1.00
    /**
    0.99
     كومونز
    0.97
    httphttps
    0.96
    Activations Density 0.177%

    No Known Activations