Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 38
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in sentences

    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
     purpoſe
    -1.34
     Económica
    -1.31
     Monfieur
    -1.29
     houſe
    -1.26
     ſeveral
    -1.25
     Diſ
    -1.22
     greateſt
    -1.21
     Reſ
    -1.18
     Constitucional
    -1.17
     Moisés
    -1.17
    POSITIVE LOGITS
     „
    0.73
     im
    0.67
     der
    0.67
     für
    0.66
     zu
    0.65
     ‚
    0.63
     und
    0.63
     um
    0.62
     mit
    0.61
     wo
    0.61
    Activations Density 0.132%

    No Known Activations