© 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. 6996
    Prev
    Next
    INDEX
    Explanations

    character names and titles associated with specific series or media

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

    Kamen Rider and Super Sentai series

    np_acts-logits-general · gemini-2.0-flash

    Kamen Rider, Super Sentai

    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
     Monfieur
    -0.58
     Theſe
    -0.56
     leaſt
    -0.52
     >=",
    -0.51
     itſelf
    -0.50
    **
    -0.50
     pleaſure
    -0.50
     purpoſe
    -0.50
    ^(@)
    -0.50
     theſe
    -0.49
    POSITIVE LOGITS
    ########.
    0.65
     veran
    0.61
     EX
    0.58
    tvguidetime
    0.58
     mecha
    0.56
    Tembelea
    0.56
    WebServlet
    0.56
    TypedDataSet
    0.56
     Gundam
    0.55
    bitset
    0.55
    Activations Density 0.474%

    No Known Activations