© 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. 8309
    Prev
    Next
    INDEX
    Explanations

    symbols and characters commonly used in academic or technical writing

    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
     queſta
    -0.78
     itſelf
    -0.75
     abstrait
    -0.75
     myſelf
    -0.75
     leſs
    -0.74
    〮
    -0.73
     surla
    -0.71
    
    -0.71
    ðsíða
    -0.71
     kasarigan
    -0.71
    POSITIVE LOGITS
     BorderSide
    0.34
    \{\\
    0.31
    addCriterion
    0.30
    .*")]
    0.28
    op
    0.27
    w
    0.25
    FieldBuilder
    0.24
     radio
    0.23
    штей
    0.22
     m
    0.22
    Activations Density 0.277%

    No Known Activations