© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30001
    Prev
    Next
    INDEX
    Explanations

    instances of text formatting or special markers

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

    names preceding pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جغرافيا
    -0.56
    wijl
    -0.56
     '\\;'
    -0.50
    多么
    -0.49
     муніципалі
    -0.48
     pessoais
    -0.47
    http
    -0.46
    antMatchers
    -0.45
     JADX
    -0.45
     kaynağından
    -0.45
    POSITIVE LOGITS
    </h4>
    1.01
    </h3>
    0.89
    </h2>
    0.89
    :✨
    0.85
     autorytatywna
    0.80
    Autoritní
    0.76
    </h1>
    0.75
    </h5>
    0.74
    )$}
    0.72
    PRWEB
    0.71
    Activations Density 0.034%

    No Known Activations