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. 0-GEMMASCOPE-RES-16K
    6. 6777
    Prev
    Next
    INDEX
    Explanations

    references to governing bodies or councils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Socialism
    -0.53
     !=
    -0.47
     eggs
    -0.45
     prefrontal
    -0.45
    chot
    -0.44
     définition
    -0.44
     aberration
    -0.43
     روان
    -0.42
     verg
    -0.42
    woli
    -0.42
    POSITIVE LOGITS
    TagMode
    1.05
     council
    1.00
     Council
    0.98
    parsedMessage
    0.97
    Council
    0.97
    council
    0.96
    ParallelGroup
    0.95
    '));
    
    0.94
     ModelExpression
    0.93
    istoitu
    0.92
    Activations Density 0.127%

    No Known Activations