© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16041
    Prev
    Next
    INDEX
    Explanations

    technical terms related to standardization and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    TeX commands and formatting

    np_acts-logits-general · gemini-2.0-flash

    mathematical and latex typesetting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Macdonald
    -0.83
     Bennet
    -0.79
    varepsilon
    -0.78
     yoghurt
    -0.76
     Whatsapp
    -0.73
     Chilli
    -0.72
     ∆
    -0.71
     omelette
    -0.71
     whisky
    -0.71
     enquiry
    -0.70
    POSITIVE LOGITS
     Gray
    0.93
     gage
    0.93
    Gray
    0.84
     glycerin
    0.83
     Wilder
    0.80
     GRAY
    0.80
     gray
    0.76
     Emerson
    0.75
     railroad
    0.75
     Theater
    0.74
    Activations Density 1.569%

    No Known Activations