© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8962
    Prev
    Next
    INDEX
    Explanations

    expressions of positive attributes or evaluations

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

    Preceding "day", "idea", "number", "friend", "job", "player", or "source"

    np_acts-logits-general · gemini-2.0-flash

    positive evaluations of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incredible
    -0.39
     absolutely
    -0.37
     incredibly
    -0.37
    AbsolutePath
    -0.36
     revolution
    -0.36
     unparalleled
    -0.34
    TypedDataSet
    -0.34
     instantly
    -0.33
    rawQuery
    -0.33
     flying
    -0.33
    POSITIVE LOGITS
     decent
    0.87
     непло
    0.83
    Decent
    0.81
     decently
    0.77
     Decent
    0.77
     creditable
    0.76
     intéressant
    0.74
     interesante
    0.74
    interesting
    0.71
     Interesting
    0.70
    Activations Density 0.508%

    No Known Activations