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. 687
    Prev
    Next
    INDEX
    Explanations

    formal research terminology and aims in scientific studies

    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
     bocca
    -0.63
    )++;
    -0.60
    )"),
    -0.57
     onOptions
    -0.56
     faccia
    -0.56
     tramonto
    -0.55
    MergeFrom
    -0.55
    yntaxException
    -0.55
    нциклопе
    -0.54
     trás
    -0.52
    POSITIVE LOGITS
     present
    1.50
     study
    1.32
    present
    1.31
     presente
    1.24
     paper
    1.22
     présent
    1.20
    Present
    1.13
    study
    1.11
     Present
    1.11
    paper
    1.08
    Activations Density 1.098%

    No Known Activations