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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 6140
    Prev
    Next
    INDEX
    Explanations

    expressions and symbols related to mathematical concepts and matrices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMPORTED
    -0.56
     Tham
    -0.52
     muualla
    -0.50
     next
    -0.49
     rhyme
    -0.49
    forsch
    -0.48
     cams
    -0.44
    śred
    -0.42
    WhereInput
    -0.42
     espont
    -0.40
    POSITIVE LOGITS
    󠁿
    0.94
    RectangleBorder
    0.75
     ویکی‌پدی
    0.74
    Geplaatst
    0.72
    StoryboardSegue
    0.71
     defaultstate
    0.69
    AndEndTag
    0.69
     Italijanski
    0.69
    tvguidetime
    0.68
    Rujuakan
    0.67
    Activations Density 2.782%

    No Known Activations