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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7892
    Prev
    Next
    INDEX
    Explanations

    references to the value and quality of reading material

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

    Tokens preceding "reading" or "read"

    np_acts-logits-general · gemini-2.0-flash

    recommendations for reading

    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
    yntaxException
    -0.61
    帖最后由
    -0.61
     CreateTagHelper
    -0.57
     mxArray
    -0.56
     ***!
    -0.56
    WSGI
    -0.55
    цездатний
    -0.55
    elemField
    -0.53
    TestTools
    -0.51
     الفلك
    -0.51
    POSITIVE LOGITS
     reading
    2.41
     read
    2.34
    reading
    1.93
     reads
    1.89
    read
    1.86
     Reading
    1.79
    Reading
    1.76
     READING
    1.74
     Read
    1.61
     readings
    1.60
    Activations Density 0.556%

    No Known Activations