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. 12-GEMMASCOPE-RES-16K
    6. 15510
    Prev
    Next
    INDEX
    Explanations

    references to different systems, particularly those related to technology and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.61
    ----</
    -0.56
     EconPapers
    -0.55
    welijk
    -0.52
    heard
    -0.51
    存于互联网档案馆
    -0.49
    permum
    -0.49
    WireFormat
    -0.48
     Heard
    -0.48
    enovo
    -0.48
    POSITIVE LOGITS
     NSCoder
    0.59
     décrire
    0.54
    Personensuche
    0.54
     whoſe
    0.53
     qualités
    0.53
    RenderAtEndOf
    0.52
    */;
    0.51
    زیین
    0.51
    matchCondition
    0.50
    सनीय
    0.50
    Activations Density 1.341%

    No Known Activations