© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 4478
    Prev
    Next
    INDEX
    Explanations

    the character 'a' in various contexts within the text

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

    "a" followed by code or math symbols

    np_acts-logits-general · gemini-2.0-flash

    a followed by punctuation or code characters

    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
    quela
    -0.63
    quilo
    -0.62
    m
    -0.60
     affrontare
    -0.60
    NamedQueries
    -0.58
    queles
    -0.55
    ly
    -0.54
     avere
    -0.54
    ven
    -0.54
    g
    -0.53
    POSITIVE LOGITS
     aVar
    0.91
    aaaa
    0.73
    aaa
    0.72
    aaaaa
    0.70
    aaaaaaaa
    0.68
     href
    0.67
    tableFuture
    0.66
    
    0.66
    aaaaaa
    0.64
    HtmlAttribute
    0.63
    Activations Density 0.381%

    No Known Activations