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. 16-GEMMASCOPE-RES-16K
    6. 1363
    Prev
    Next
    INDEX
    Explanations

    phrases indicating diversity and variety in samples or categories

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

    Large, diverse quantities or types

    np_acts-logits-general · gemini-2.0-flash

    abundance and variety

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GEBURTSDATUM
    -0.59
    zym
    -0.56
    ⓧ
    -0.50
    فات
    -0.49
    ConstraintMaker
    -0.49
    ItemLayout
    -0.49
    Примітки
    -0.47
    cuba
    -0.47
    GroupLayout
    -0.46
    iastes
    -0.46
    POSITIVE LOGITS
     assortment
    0.97
     plethora
    0.89
     array
    0.80
     multitude
    0.80
    agerie
    0.80
     myriad
    0.78
     gamut
    0.76
     collection
    0.76
     range
    0.75
    HtmlAttribute
    0.73
    Activations Density 0.249%

    No Known Activations