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. 1-GEMMASCOPE-RES-16K
    6. 14964
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to science and technology, particularly in the fields of molecular biology and physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dota
    -0.60
     Hickey
    -0.59
     riuscito
    -0.59
    limo
    -0.59
    knex
    -0.58
     IActionResult
    -0.55
    RectangleBorder
    -0.55
     Gesta
    -0.55
    mybatisplus
    -0.54
    tableFuture
    -0.54
    POSITIVE LOGITS
     Spinning
    0.97
    Spinning
    0.90
     spinning
    0.87
     rotates
    0.85
     rotation
    0.84
     Rotation
    0.83
     rotating
    0.83
     rotations
    0.83
     Spin
    0.81
     rotate
    0.81
    Activations Density 2.657%

    No Known Activations