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. 4-GEMMASCOPE-RES-16K
    6. 11008
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time, particularly concerning years or significant intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.77
     StringTokenizer
    -0.62
     vPvB
    -0.62
    Trama
    -0.57
    iastes
    -0.57
     zelve
    -0.56
    ➯
    -0.54
     متعلقه
    -0.54
     beispiel
    -0.53
    كامل
    -0.52
    POSITIVE LOGITS
     NSCoder
    0.68
     EconPapers
    0.65
    年後
    0.57
    EDEFAULT
    0.53
     спустя
    0.53
    laven
    0.51
    BufferException
    0.50
    rungsseite
    0.49
     after
    0.49
    after
    0.48
    Activations Density 0.208%

    No Known Activations