© 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. 22-GEMMASCOPE-RES-16K
    6. 8562
    Prev
    Next
    INDEX
    Explanations

    headings or section titles within a document

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

    HTML heading tags (h1-h6, h3, h4)

    np_acts-logits-general · gemini-2.0-flash

    Name Eun Lee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.25
    NUMX
    -1.21
    LLocation
    -1.05
    AllAfrica
    -1.04
    EDEFAULT
    -1.00
     Efq
    -0.99
     Савезне
    -0.96
     FetchType
    -0.93
    ^(@)
    -0.90
    leſs
    -0.90
    POSITIVE LOGITS
    <h3>
    1.14
    <eos>
    1.08
    ↵↵
    0.97
    <h4>
    0.96
    <h2>
    0.94
    <h1>
    0.90
    ↵
    0.89
    <h5>
    0.88
    <b>
    0.85
    ↵↵↵
    0.81
    Activations Density 0.108%

    No Known Activations