© 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. 10615
    Prev
    Next
    INDEX
    Explanations

    terms related to ranking and classifications

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

    Numbers following specific words ("rank", "page", "order")

    np_acts-logits-general · gemini-2.0-flash

    numbers following rank or phase

    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
    SequentialGroup
    -0.56
     Diſ
    -0.54
    第二次
    -0.51
    中略
    -0.49
    Portail
    -0.48
    حياتها
    -0.45
    ImageContext
    -0.44
    urez
    -0.44
     Saltar
    -0.44
     незавершена
    -0.43
    POSITIVE LOGITS
     twos
    1.07
     Two
    1.00
     zero
    0.97
     two
    0.97
    two
    0.95
    TWO
    0.95
     four
    0.94
     TWO
    0.94
     FIVE
    0.94
     Four
    0.94
    Activations Density 0.617%

    No Known Activations