Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14682
    Prev
    Next
    INDEX
    Explanations

    terms related to turbidity and its measurement in various contexts

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

    that start with "Tur"

    np_acts-logits-general · gemini-2.0-flash

    Tur, Turb, Turgesh, Turmeric, Turkiye

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    classmethod
    -0.67
    gatsby
    -0.63
     désolés
    -0.60
    databind
    -0.59
     Vì
    -0.58
    region
    -0.55
    :+:
    -0.55
    orse
    -0.55
    Legends
    -0.54
    ably
    -0.54
    POSITIVE LOGITS
    NameInMap
    0.76
    ContentAsync
    0.75
     Мексичка
    0.68
     CHtml
    0.66
     ​​
    0.65
    日閲覧
    0.61
    addCriterion
    0.60
     endforeach
    0.60
    Manif
    0.59
     overs
    0.58
    Activations Density 0.483%

    No Known Activations