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. 2403
    Prev
    Next
    INDEX
    Explanations

    mentions of sodium and related compounds

    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
     Wheeler
    -0.68
    Atsauces
    -0.67
     nekaj
    -0.67
     Brock
    -0.67
    龟
    -0.63
    اخ
    -0.63
     fior
    -0.61
    Vey
    -0.60
     vš
    -0.60
    matchCondition
    -0.60
    POSITIVE LOGITS
     Na
    2.29
    Na
    2.23
     na
    1.82
     NA
    1.49
     Naidu
    1.45
    na
    1.41
     sodium
    1.38
     Naik
    1.36
     Nadel
    1.32
     Sodium
    1.30
    Activations Density 0.094%

    No Known Activations