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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5174
    Prev
    Next
    INDEX
    Explanations

    words related to specific processes or actions, particularly in technical and operational contexts

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

    ending in "-ing" or related to drying/processing

    np_acts-logits-general · gemini-2.0-flash

    actions followed by "-ing" or "-ting"

    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
     sağlar
    -0.66
     kullanılır
    -0.61
     sahiptir
    -0.60
     trône
    -0.57
     démocr
    -0.56
     bulunur
    -0.55
    lanır
    -0.53
     yapılır
    -0.53
     चीज़ों
    -0.52
     prévue
    -0.50
    POSITIVE LOGITS
     making
    1.37
     getting
    1.37
     taking
    1.25
     creating
    1.24
     putting
    1.24
     delivering
    1.23
     doing
    1.23
     being
    1.22
     giving
    1.17
     adding
    1.17
    Activations Density 0.594%

    No Known Activations