© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13363
    Prev
    Next
    INDEX
    Explanations

    technical issues or errors in programming and software development contexts

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

    Followed by "user"

    np_acts-logits-general · gemini-2.0-flash

    Nigeria and Africa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     iconTwitter
    -0.43
     ביום
    -0.40
    󠁬
    -0.40
    ʌ
    -0.39
    XmlAccessorType
    -0.39
     ramping
    -0.38
     παρα
    -0.35
    addPreferredGap
    -0.34
     упо
    -0.34
    sstelle
    -0.34
    POSITIVE LOGITS
     Nigeria
    0.66
     African
    0.64
     Nigerian
    0.62
    African
    0.59
    Nigeria
    0.58
     africains
    0.57
     Africa
    0.57
     Africans
    0.56
    Nigerian
    0.56
     african
    0.55
    Activations Density 0.203%

    No Known Activations