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. 20-GEMMASCOPE-RES-16K
    6. 14417
    Prev
    Next
    INDEX
    Explanations

    structured data elements and their properties in a programming or API context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.62
     jspb
    -0.62
     autorytatywna
    -0.61
     contextLoads
    -0.60
    abetes
    -0.58
    ThroughAttribute
    -0.57
    PropertyChanging
    -0.56
    брь
    -0.56
     pleaſure
    -0.53
     AssemblyTitle
    -0.53
    POSITIVE LOGITS
     "?
    0.89
     '?
    0.86
    }?
    0.83
    ="?
    0.80
     URL
    0.79
     query
    0.79
     '?'
    0.78
     url
    0.78
    ?
    0.76
    /?
    0.75
    Activations Density 0.216%

    No Known Activations