© 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. 13360
    Prev
    Next
    INDEX
    Explanations

    expressions of strengths, qualities, and positive attributes

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

    followed by "of" or "is"

    np_acts-logits-general · gemini-2.0-flash

    unique qualities and strengths

    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
    Tembelea
    -0.46
    avigation
    -0.44
     AssemblyTitle
    -0.43
    ㎢
    -0.37
    oflavin
    -0.36
    HomeAsUpEnabled
    -0.36
    kje
    -0.34
    woordig
    -0.34
    imanapun
    -0.34
     Disorders
    -0.34
    POSITIVE LOGITS
     uniqueness
    0.68
     unique
    0.62
     Unique
    0.56
     UNIQUE
    0.56
     Besonder
    0.55
    unique
    0.54
     peculiarity
    0.53
    Unique
    0.52
    特徴
    0.52
     unik
    0.52
    Activations Density 0.427%

    No Known Activations