© 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. 16-GEMMASCOPE-RES-16K
    11. 13025
    Prev
    Next
    INDEX
    Explanations

    patterns or structures related to coding and programming concepts, specifically involving thread management and object-oriented programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.88
    ſelf
    -0.84
     betweenstory
    -0.82
     OMITBAD
    -0.77
     Houſe
    -0.77
     queſta
    -0.75
     houſe
    -0.74
    ſelves
    -0.74
     ſche
    -0.73
    ſchen
    -0.73
    POSITIVE LOGITS
    The
    0.55
    if
    0.53
     The
    0.47
    A
    0.45
     $
    0.45
    kirakan
    0.45
     if
    0.44
    How
    0.41
     dă
    0.40
    :
    0.40
    Activations Density 0.080%

    No Known Activations