© 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. 12322
    Prev
    Next
    INDEX
    Explanations

    instances of the word "introduction" and its variations

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

    "Introduction" followed by a section number

    np_acts-logits-general · gemini-2.0-flash

    introduction headings or sections

    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
    FormItem
    -0.48
     S
    -0.46
     от
    -0.45
    ΜΑ
    -0.45
    花板
    -0.45
     B
    -0.43
     K
    -0.43
     bề
    -0.43
    en
    -0.42
    getFrom
    -0.42
    POSITIVE LOGITS
    fjspx
    1.21
    ductory
    1.17
    OGND
    1.12
     Introduce
    1.08
     ویکی‌پدی
    1.05
     Roskov
    1.04
     препратки
    1.01
     myſelf
    1.00
     itſelf
    1.00
     متعلقه
    1.00
    Activations Density 0.069%

    No Known Activations