© 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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 9263
    Prev
    Next
    INDEX
    Explanations

    numerical scores or statistics related to sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 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
     ddelweddau
    -0.76
     niedersachsen
    -0.73
    +#+#
    -0.72
    ſelf
    -0.70
     Theſe
    -0.63
     itſelf
    -0.63
     himſelf
    -0.62
     Majefty
    -0.62
     ſtill
    -0.61
    neſs
    -0.61
    POSITIVE LOGITS
    istici
    0.52
    firestore
    0.52
    Datuak
    0.49
     AssemblyProduct
    0.49
    EDEFAULT
    0.48
    串
    0.45
     DataTypes
    0.45
    ">—
    0.45
    autique
    0.43
     moradores
    0.43
    Activations Density 0.024%

    No Known Activations