© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 9236
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.85
    rungsseite
    -0.81
     AssemblyCulture
    -0.78
     typelib
    -0.71
    jsii
    -0.71
    GEBURTSDATUM
    -0.70
    новништво
    -0.66
     parmi
    -0.66
    msgTypes
    -0.66
    ंदीखरीदारी
    -0.65
    POSITIVE LOGITS
     hinweg
    0.77
     heen
    0.70
     hindurch
    0.67
     channels
    0.44
     unsc
    0.40
     hinaus
    0.37
     gau
    0.35
     gates
    0.35
     like
    0.35
     lens
    0.35
    Activations Density 0.452%

    No Known Activations