© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 6498
    Prev
    Next
    INDEX
    Explanations

    names of artists and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Buc
    -1.08
     Buc
    -1.06
     Koc
    -0.95
     PGC
    -0.94
     Kac
    -0.93
    ac
    -0.91
     Hac
    -0.90
     Nac
    -0.90
     Dic
    -0.87
    Hec
    -0.86
    POSITIVE LOGITS
     lenker
    0.89
    허
    0.89
     parseFrom
    0.88
    dehyde
    0.85
    dehydes
    0.84
     himo
    0.83
     zewnętrzne
    0.82
    oughly
    0.82
     CGA
    0.80
     referenties
    0.80
    Activations Density 1.337%

    No Known Activations