© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15895
    Prev
    Next
    INDEX
    Explanations

    special formatting or non-alphanumeric characters

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

    Text before a question mark, "Q:"

    np_acts-logits-general · gemini-2.0-flash

    Q followed by question or list items

    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
    HtmlAttribute
    -0.75
    :+:
    -0.69
     initComponents
    -0.67
    mobileqq
    -0.63
     समीक्षक
    -0.61
    bitField
    -0.61
     <>",
    -0.60
     Photocase
    -0.60
    LookAnd
    -0.59
    MENAFN
    -0.58
    POSITIVE LOGITS
    ScopeManager
    1.60
     саны
    0.57
    recogn
    0.52
    STIC
    0.49
     ло
    0.47
    redient
    0.47
    Suomen
    0.47
     breath
    0.46
    guri
    0.46
    Gecko
    0.46
    Activations Density 0.042%

    No Known Activations