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. 3385
    Prev
    Next
    INDEX
    Explanations

    references to the name "Le" in various contexts

    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
    LikeLike
    -0.93
     Bahnhof
    -0.72
     MessageBoxIcon
    -0.72
    eabouts
    -0.71
    DotNetBar
    -0.71
    ness
    -0.70
     faim
    -0.69
    findpost
    -0.66
     Tess
    -0.64
     Newsroom
    -0.64
    POSITIVE LOGITS
     Le
    2.00
    Le
    1.99
     le
    1.79
     LE
    1.62
    LE
    1.59
    le
    1.55
     Leighton
    1.20
     Leona
    1.16
     Ле
    1.13
     Leicestershire
    1.13
    Activations Density 0.074%

    No Known Activations