© 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. 4420
    Prev
    Next
    INDEX
    Explanations

    phrases related to the measurement or definition of time frames in research contexts

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

    Definition or meaning of a word

    np_acts-logits-general · gemini-2.0-flash

    what that means

    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
    endphp
    -0.54
    ftagPool
    -0.53
    ільки
    -0.47
    いかがでしょうか
    -0.47
    ziu
    -0.46
     تضيفلها
    -0.45
    PYX
    -0.43
    ChildScrollView
    -0.43
    ailleurs
    -0.43
    Citiți
    -0.43
    POSITIVE LOGITS
     means
    3.06
     meaning
    2.73
    means
    2.71
     Means
    2.60
     mean
    2.56
     MEANS
    2.50
    Means
    2.46
     MEAN
    2.36
    meaning
    2.36
    Meaning
    2.33
    Activations Density 0.731%

    No Known Activations