© 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. 1-GEMMASCOPE-RES-16K
    11. 3654
    Prev
    Next
    INDEX
    Explanations

    references to episodes in a series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    front
    -0.47
    Front
    -0.40
    FRONT
    -0.37
    mployment
    -0.36
     "../../../
    -0.36
    Land
    -0.35
     Front
    -0.35
    Халык
    -0.35
    客様
    -0.34
     '../../
    -0.34
    POSITIVE LOGITS
     Period
    0.70
     periods
    0.69
     period
    0.68
    Personensuche
    0.68
     Periods
    0.67
     methodology
    0.66
    Episodes
    0.65
     episodes
    0.63
     nonUne
    0.63
     للمعارف
    0.63
    Activations Density 0.190%

    No Known Activations