© 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. 9339
    Prev
    Next
    INDEX
    Explanations

    the start of a document or section, typically indicated by special tokens like <bos>

    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
    tagHelperRunner
    -0.61
     للمعارف
    -0.53
     opérateur
    -0.51
    Selfer
    -0.51
     épouse
    -0.50
     tartalomajánló
    -0.50
     resourceCulture
    -0.50
     propriétaire
    -0.49
    nezeu
    -0.48
     ब्रेकडाउन
    -0.48
    POSITIVE LOGITS
     const
    0.90
    const
    0.76
    constexpr
    0.60
     constexpr
    0.51
     constant
    0.47
    Const
    0.46
     Const
    0.46
    <thead>
    0.43
     constants
    0.42
     StatefulWidget
    0.42
    Activations Density 0.028%

    No Known Activations