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. 10-GEMMASCOPE-RES-16K
    6. 12659
    Prev
    Next
    INDEX
    Explanations

    keywords related to real estate and aviation industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Psychologist
    -0.76
     olympique
    -0.74
     Scientist
    -0.74
     réguli
    -0.73
     Verstappen
    -0.71
    nosaurus
    -0.71
     démocr
    -0.70
     Bucure
    -0.70
    izielle
    -0.70
     Colombie
    -0.70
    POSITIVE LOGITS
     />";
    0.78
     services
    0.75
     />';
    0.71
    />";
    0.71
     industry
    0.70
    ?')
    0.70
    ."</
    0.69
     كومونز
    0.68
    ?")
    0.66
    crafts
    0.65
    Activations Density 0.506%

    No Known Activations