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. 20-GEMMASCOPE-RES-16K
    6. 1254
    Prev
    Next
    INDEX
    Explanations

    terms related to gastrointestinal and liver conditions

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

    Terms related to the digestive system

    np_acts-logits-general · gemini-2.0-flash

    gastrointestinal symptoms or conditions

    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
     rencont
    -0.46
     présentes
    -0.46
     élevées
    -0.46
    ojo
    -0.46
     okuyayım
    -0.46
    はじめに
    -0.45
     marquées
    -0.45
    +][
    -0.44
    ★★★★☆
    -0.44
     emporter
    -0.44
    POSITIVE LOGITS
    \{\\
    0.78
     Audiodateien
    0.74
     tract
    0.69
     MatDialog
    0.65
    :✨
    0.65
    XmlAccessorType
    0.64
     BorderRadius
    0.64
    InjectMocks
    0.64
     betweenstory
    0.62
     Tract
    0.62
    Activations Density 0.830%

    No Known Activations