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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1730
    Prev
    Next
    INDEX
    Explanations

    important numerical results or values in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цио
    -0.56
    akan
    -0.54
    aw
    -0.54
     mit
    -0.51
     #
    -0.50
     ALL
    -0.49
     mb
    -0.49
    les
    -0.48
     Mit
    -0.48
    sa
    -0.47
    POSITIVE LOGITS
    تقاوى
    0.79
    ValueGeneration
    0.75
    Datuak
    0.75
    sizeCache
    0.74
    findpost
    0.73
    WriteTagHelper
    0.71
     poveznice
    0.71
    .*")]
    0.70
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.70
    ")));
    
    0.70
    Activations Density 0.296%

    No Known Activations