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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 7496
    Prev
    Next
    INDEX
    Explanations

    XML or structured data elements related to project configuration

    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
    (!__
    -0.61
    antas
    -0.57
     mobile
    -0.52
     Mobile
    -0.51
    Mobile
    -0.49
    mobile
    -0.48
     MOBILE
    -0.48
     impress
    -0.48
     الدولى
    -0.48
    เย
    -0.46
    POSITIVE LOGITS
    TemporalType
    0.72
    MigrationBuilder
    0.67
     âgées
    0.62
    ConstraintMaker
    0.61
     colorés
    0.60
     dependencia
    0.59
     package
    0.59
    HasAnnotation
    0.59
    LError
    0.56
     Package
    0.56
    Activations Density 0.410%

    No Known Activations