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. 3-GEMMASCOPE-RES-16K
    6. 12068
    Prev
    Next
    INDEX
    Explanations

    references to various kinds of people, authority, and categorization in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numerus
    -0.69
     विश्वसनीयता
    -0.69
    WriteTagHelper
    -0.57
    Clik
    -0.56
     nahilalakip
    -0.55
     büyü
    -0.55
    createCanvas
    -0.54
    AndroidJUnit
    -0.54
    Cyfeiriadau
    -0.54
    Synonymes
    -0.53
    POSITIVE LOGITS
    หวัด
    0.51
    WebVitals
    0.51
    messageInfo
    0.50
    InjectAttribute
    0.50
    ulink
    0.49
     mellitus
    0.47
     RoutedEventArgs
    0.46
    IImage
    0.46
     NUKAT
    0.45
    Portail
    0.43
    Activations Density 1.787%

    No Known Activations