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. 3895
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds, particularly those related to metals and their properties

    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
     snippetHide
    -1.06
    adaptiveStyles
    -0.92
    
    -0.89
    __":
    
    -0.85
     defaultstate
    -0.80
     مشين
    -0.80
    __':
    
    -0.79
     الرياضيه
    -0.76
    Autoritní
    -0.76
    ptid
    -0.75
    POSITIVE LOGITS
     sodium
    0.98
     Sodium
    0.95
    Sodium
    0.91
    sodium
    0.88
     Na
    0.84
     Potassium
    0.79
     sodio
    0.79
    assium
    0.78
     potassium
    0.77
    Na
    0.75
    Activations Density 0.339%

    No Known Activations