© 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. 12-GEMMASCOPE-RES-16K
    11. 5355
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    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
     betweenstory
    -0.74
     autorytatywna
    -0.68
     disambiguazione
    -0.67
     незавершена
    -0.66
     للمعارف
    -0.62
    CloseOperation
    -0.61
    OGND
    -0.61
    AndEndTag
    -0.60
     HasFactory
    -0.54
    POSITIVE LOGITS
     ARR
    0.40
     detailed
    0.38
    adell
    0.38
    >>()
    0.38
     its
    0.37
    "][
    0.37
     official
    0.37
     eerie
    0.37
    aclk
    0.36
    ：</
    0.36
    Activations Density 0.341%

    No Known Activations