© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5615
    Prev
    Next
    INDEX
    Explanations

    phrases and terms indicating frequency and quantity, particularly the word "most"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adanya
    -0.48
    場合があります
    -0.48
    HS
    -0.47
    zu
    -0.47
    essä
    -0.44
     minh
    -0.44
     coordenadas
    -0.43
     ніж
    -0.43
    ว์
    -0.42
    ḥ
    -0.42
    POSITIVE LOGITS
    TagMode
    0.90
    Personendaten
    0.89
    raisemb
    0.80
    tagext
    0.79
     auffi
    0.79
     myſelf
    0.78
     виправивши
    0.77
     >=",
    0.77
     ſind
    0.76
     meisten
    0.74
    Activations Density 0.168%

    No Known Activations