© 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
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9159
    Prev
    Next
    INDEX
    Explanations

    intensely subjective expressions and emotional sentiments

    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
    astéroïdes
    -0.60
    EndContext
    -0.59
    enumi
    -0.59
     ویکی‌پدیای
    -0.56
    ocate
    -0.55
    ▾
    -0.54
    ContentLoaded
    -0.54
    togram
    -0.53
     syndic
    -0.53
    ingual
    -0.52
    POSITIVE LOGITS
    really
    1.30
     really
    1.22
     Really
    1.14
    Really
    1.14
     REALLY
    1.11
     realy
    0.88
     vraiment
    0.83
     realmente
    0.82
     wirklich
    0.76
     naprawdę
    0.75
    Activations Density 0.057%

    No Known Activations