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. 10-GEMMASCOPE-RES-16K
    6. 5769
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to data structure formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.79
     للمعارف
    -0.53
    DeleteBehavior
    -0.51
    EditorBrowsable
    -0.49
     defStyleAttr
    -0.49
    ="#"><
    -0.46
    Климат
    -0.45
     scope
    -0.45
    <>());
    -0.45
     متعلقه
    -0.45
    POSITIVE LOGITS
    JspWriter
    0.63
    NewUrlParser
    0.59
    ImageIO
    0.52
    sbericht
    0.50
    byr
    0.50
    tyfik
    0.49
    ilitation
    0.49
     témoignage
    0.49
     wall
    0.48
     giãn
    0.48
    Activations Density 0.527%

    No Known Activations