© 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. 9061
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and correlation

    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
     disadvantage
    -0.53
     eds
    -0.49
    سا
    -0.47
     steps
    -0.46
     emend
    -0.45
    Advantage
    -0.45
    iniques
    -0.44
     descend
    -0.44
     ſy
    -0.44
    #!/
    -0.43
    POSITIVE LOGITS
    correlation
    0.81
     correlation
    0.76
     Correlations
    0.73
     Correlation
    0.72
    Correlation
    0.71
     correlations
    0.71
     OFDb
    0.70
     InputDecoration
    0.66
     propOrder
    0.66
    SerializedName
    0.65
    Activations Density 0.895%

    No Known Activations