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. 24-GEMMASCOPE-RES-16K
    6. 2313
    Prev
    Next
    INDEX
    Explanations

    intensifiers and modifiers that emphasize degree or extent

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

    Adverbs modifying degree (more, very, so, quite, as)

    np_acts-logits-general · gemini-2.0-flash

    adverbs of manner and intensity

    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
     lepší
    -0.66
     récentes
    -0.65
     quelcon
    -0.62
     malheureux
    -0.60
     démocr
    -0.60
    Datuak
    -0.60
     nejlepší
    -0.59
     courants
    -0.58
     faibles
    -0.58
     récente
    -0.57
    POSITIVE LOGITS
     quickly
    1.02
     regularly
    0.91
     successfully
    0.91
     efficiently
    0.91
     comprehensively
    0.89
     seamlessly
    0.88
     effectively
    0.87
    quickly
    0.87
     effortlessly
    0.86
     urgently
    0.86
    Activations Density 0.182%

    No Known Activations