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. 21-GEMMASCOPE-RES-16K
    6. 7311
    Prev
    Next
    INDEX
    Explanations

    references to academic departments and their accreditation status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sotheby
    -0.54
    otheby
    -0.47
    rairie
    -0.47
    ViewFeatures
    -0.47
    DDB
    -0.46
    LDA
    -0.45
    SequentialGroup
    -0.45
    ymce
    -0.45
     darts
    -0.44
     Clarissa
    -0.44
    POSITIVE LOGITS
     engineering
    1.92
     engineers
    1.78
     Engineering
    1.75
     engineer
    1.71
     Engineers
    1.65
     Engineer
    1.63
    Engineering
    1.62
    engineering
    1.60
    Engineers
    1.57
     ENGINEERING
    1.55
    Activations Density 0.258%

    No Known Activations