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. 16-GEMMASCOPE-RES-16K
    6. 12292
    Prev
    Next
    INDEX
    Explanations

    sequences of nested mathematical symbols and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX math delimiters

    np_acts-logits-general · gemini-2.0-flash

    }{ and d/dt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hanson
    -0.68
     Mandela
    -0.66
     Anderson
    -0.65
     déb
    -0.65
    ůměr
    -0.63
     Guen
    -0.63
     Hansen
    -0.62
    icha
    -0.62
     events
    -0.62
     bar
    -0.59
    POSITIVE LOGITS
    )}{
    1.20
    }{
    1.13
    )}}{
    1.08
     }}}{
    1.04
    ]}{
    1.03
    |}{
    1.00
    __':
    0.96
     }{
    0.96
    __':
    
    0.94
    }}}{
    0.92
    Activations Density 0.247%

    No Known Activations