© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9669
    Prev
    Next
    INDEX
    Explanations

    references to social issues and the complexities of societal norms

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

    current or recent time

    np_acts-logits-general · gemini-2.0-flash

    these days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ervlak
    -0.55
    Искәрмәләр
    -0.52
    LEncoder
    -0.50
    ientras
    -0.49
     Perſ
    -0.47
     Previous
    -0.47
     PREVIOUS
    -0.47
     ſind
    -0.46
     precedente
    -0.46
     iſt
    -0.45
    POSITIVE LOGITS
     nowadays
    2.72
     Nowadays
    1.98
    Nowadays
    1.95
     heut
    1.76
     today
    1.59
    woordig
    1.59
     lately
    1.47
     anymore
    1.40
    最近は
    1.32
     mittlerweile
    1.31
    Activations Density 0.653%

    No Known Activations