Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12699
    Prev
    Next
    INDEX
    Explanations

    references to research, reports, and literature searches

    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
    الحياه
    -0.78
    SBATCH
    -0.63
     newBuilder
    -0.62
    numerusform
    -0.59
     مواليد
    -0.58
    Tembelea
    -0.57
    SequentialGroup
    -0.54
    SerializedSize
    -0.53
    mobileqq
    -0.52
     Biôgrafia
    -0.51
    POSITIVE LOGITS
     literature
    0.78
    literature
    0.74
     publications
    0.65
     Theſe
    0.63
     websites
    0.63
     online
    0.62
     littérature
    0.60
     articles
    0.58
    出版年
    0.57
    Literature
    0.57
    Activations Density 0.576%

    No Known Activations