© 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. 0-GEMMASCOPE-RES-16K
    11. 8391
    Prev
    Next
    INDEX
    Explanations

    references to padding or pads in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.80
    ,
    -0.76
    .
    -0.72
    ↵↵
    -0.71
     the
    -0.70
    ↵
    -0.70
     a
    -0.68
    1
    -0.68
      
    -0.66
     (
    -0.66
    POSITIVE LOGITS
     queſta
    1.21
     zijne
    1.19
     незавершена
    1.17
     avoient
    1.16
     ainfi
    1.11
     desmotivaciones
    1.10
     étoient
    1.09
    <unused23>
    1.08
    <unused3>
    1.08
    <pad>
    1.08
    Activations Density 0.416%

    No Known Activations