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. 2910
    Prev
    Next
    INDEX
    Explanations

    terms related to theatrical productions and playwrights

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

    followed by punctuation or "the"

    np_acts-logits-general · gemini-2.0-flash

    0 times, context, execution time

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     myſelf
    -1.11
     Efq
    -1.10
     Majefty
    -1.06
     itſelf
    -1.06
     Jefus
    -1.06
     pleaſure
    -1.05
    ſelf
    -1.05
     faſt
    -1.04
     iſt
    -1.03
     purpoſe
    -1.01
    POSITIVE LOGITS
     Kontext
    0.53
    makeConstraints
    0.48
     […]
    0.47
     naviguant
    0.46
     pensieri
    0.46
    цуз
    0.46
     verrez
    0.45
    vertx
    0.45
    context
    0.45
     bParam
    0.45
    Activations Density 0.084%

    No Known Activations