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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53701
    Prev
    Next
    INDEX
    Explanations

    percentages and numeric data related to scientific measurements

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     counter
    -0.86
     COUNTER
    -0.79
    clockwise
    -0.72
    Personensuche
    -0.71
     Counter
    -0.70
     counters
    -0.68
    counter
    -0.68
    Counter
    -0.65
    TintMode
    -0.60
    windowFixed
    -0.60
    POSITIVE LOGITS
    OrNil
    0.60
     scolaires
    0.54
    stus
    0.52
     charité
    0.51
     oprot
    0.50
     koste
    0.50
    Xna
    0.50
     став
    0.48
     africains
    0.48
     canali
    0.48
    Activations Density 0.236%

    No Known Activations