© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12665
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and complexity notations involving orders of growth

    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
     amig
    -0.54
    InjectAttribute
    -0.54
    Diwedd
    -0.53
     חיצוניים
    -0.53
     StatelessWidget
    -0.52
    SequentialGroup
    -0.51
    ivers
    -0.51
    GeneratedMessage
    -0.51
     Preisen
    -0.50
    neum
    -0.47
    POSITIVE LOGITS
    enderror
    0.71
    abetes
    0.67
     متعلقه
    0.64
     مرئيه
    0.63
    Portale
    0.61
    elemField
    0.61
    躇
    0.58
    iastes
    0.57
    rawValue
    0.55
     mérito
    0.54
    Activations Density 0.626%

    No Known Activations