© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8392
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to web design, specifically those concerning fonts and their use in applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     promising
    -0.41
     brilliant
    -0.38
     and
    -0.37
     excellent
    -0.36
    Prom
    -0.35
     Tatsache
    -0.35
     steder
    -0.35
    The
    -0.34
     properties
    -0.33
     the
    -0.33
    POSITIVE LOGITS
     ब्रेकडाउन
    0.86
    enumii
    0.86
     Numerade
    0.78
    WebVitals
    0.77
    Tembelea
    0.77
     Roskov
    0.77
     незавершена
    0.75
     queſta
    0.73
    uxxxx
    0.72
    Manbalar
    0.72
    Activations Density 5.425%

    No Known Activations