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. 8067
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and experimental results in material science

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

    Liquids, interfaces, and surface tension

    np_acts-logits-general · gemini-2.0-flash

    droplet settling

    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
    webElementGuid
    -0.58
     ModelExpression
    -0.56
    podar
    -0.53
     nahilalakip
    -0.52
     Maize
    -0.52
    ьаж
    -0.51
    kyou
    -0.51
     oficial
    -0.51
     lenker
    -0.50
    Lähteet
    -0.49
    POSITIVE LOGITS
     droplet
    0.78
     settling
    0.75
     sedimentation
    0.72
     drop
    0.72
     drops
    0.71
     interfacial
    0.70
     droplets
    0.70
     Drops
    0.69
     Drop
    0.69
     DROP
    0.67
    Activations Density 1.028%

    No Known Activations