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. 5-GEMMASCOPE-RES-16K
    6. 3783
    Prev
    Next
    INDEX
    Explanations

    terms related to mononuclear cells, particularly macrophages

    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
    ValueStyle
    -0.91
     AppColors
    -0.85
     Theſe
    -0.75
     vagues
    -0.73
    ientôt
    -0.72
     tourné
    -0.72
     terbesar
    -0.71
     ReSharper
    -0.71
     behö
    -0.70
     antaranya
    -0.70
    POSITIVE LOGITS
     Mon
    2.42
    Mon
    2.23
     MON
    2.20
     mon
    2.19
    mon
    2.11
    MON
    1.98
     mono
    1.55
     Mono
    1.45
    Mono
    1.43
     MONO
    1.39
    Activations Density 0.068%

    No Known Activations