© 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. 11429
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical data and drug information

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

    Code, identifiers, or file paths

    np_acts-logits-general · gemini-2.0-flash

    datatypeid, datasetid

    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
    SuspendLayout
    -0.45
    Referanser
    -0.43
     H
    -0.42
     λί
    -0.42
    చ్
    -0.41
    fasst
    -0.41
    словно
    -0.41
     Silber
    -0.40
     informed
    -0.40
     also
    -0.40
    POSITIVE LOGITS
    ItemBackground
    0.83
    fjspx
    0.80
    ValueStyle
    0.76
    DockStyle
    0.76
    RegistryLite
    0.76
     onCancelled
    0.75
    LLocation
    0.74
    LookAnd
    0.73
     betweenstory
    0.72
    UserScript
    0.72
    Activations Density 0.513%

    No Known Activations