© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16116
    Prev
    Next
    INDEX
    Explanations

    terms related to feature detection methodologies in neural networks

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

    image feature detection and description

    np_acts-logits-general · gemini-2.0-flash

    local feature detection and description

    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
    存于互联网档案馆
    -0.63
     referrerpolicy
    -0.61
    ValueStyle
    -0.57
     SqlCommand
    -0.57
    MarshalTo
    -0.56
     للاسماء
    -0.56
    glBindBuffer
    -0.56
    InstrumentedTest
    -0.56
     systemctl
    -0.53
    ResponseWriter
    -0.52
    POSITIVE LOGITS
     feature
    0.69
     features
    0.63
    features
    0.62
     Feature
    0.61
     Features
    0.60
     FEATURE
    0.59
    feature
    0.58
     image
    0.57
    Feature
    0.56
     متعلقه
    0.56
    Activations Density 0.675%

    No Known Activations