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. 11-GEMMASCOPE-RES-16K
    6. 5787
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and their properties related to angles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -1.14
     للمعارف
    -0.91
    脚注の使い方
    -0.86
     الرخصة
    -0.85
     EconPapers
    -0.85
     telefónica
    -0.80
    expandindo
    -0.75
    లాలు
    -0.75
    RenderAtEndOf
    -0.74
     distanciation
    -0.72
    POSITIVE LOGITS
    sin
    1.22
     Sin
    1.16
     sin
    1.14
    Sin
    1.07
     cos
    1.01
     SIN
    0.99
    cos
    0.98
     sins
    0.86
     Sinclair
    0.86
    SIN
    0.85
    Activations Density 0.140%

    No Known Activations