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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 10832
    Prev
    Next
    INDEX
    Explanations

    information about challenges and guidelines related to parenting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.69
     Efq
    -0.68
     الرياضيه
    -0.67
     Shakspeare
    -0.65
     Shaksp
    -0.63
     greateſt
    -0.60
    Portale
    -0.59
     Mesozoic
    -0.58
    anskje
    -0.56
     perſon
    -0.55
    POSITIVE LOGITS
    VersionUID
    0.61
     QtCore
    0.56
    ":
    0.52
    iade
    0.50
     للاسماء
    0.49
    createClass
    0.48
    ):
    0.48
     following
    0.48
     working
    0.47
     &___
    0.47
    Activations Density 0.222%

    No Known Activations