Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 10956
    Prev
    Next
    INDEX
    Explanations

    phrases indicating commitment and quality of service in healthcare or support contexts

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

    "We are" (expressing positive sentiment)

    np_acts-logits-general · gemini-2.0-flash

    identifying "we are" followed by pride or dedication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.94
     betweenstory
    -0.87
     незавершена
    -0.84
    bootstrapcdn
    -0.72
     excru
    -0.66
    IVEREF
    -0.66
    AutoScaleMode
    -0.63
    ViewFeatures
    -0.62
    enumii
    -0.61
    ConstraintMaker
    -0.61
    POSITIVE LOGITS
     proud
    0.76
     committed
    0.59
    proud
    0.58
     pride
    0.54
     pleased
    0.54
     гор
    0.53
     orgullo
    0.53
     glad
    0.52
     expanding
    0.51
     confident
    0.49
    Activations Density 0.132%

    No Known Activations