© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 5246
    Prev
    Next
    INDEX
    Explanations

    frequent references to visits and visitation experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pos
    -0.51
     pos
    -0.46
    초
    -0.42
    cin
    -0.42
     val
    -0.41
    comp
    -0.41
     __
    -0.40
    mon
    -0.40
    que
    -0.40
    pr
    -0.40
    POSITIVE LOGITS
     visit
    1.00
     naprawdę
    0.99
     realmente
    0.92
     truly
    0.91
    truly
    0.91
     really
    0.91
    visit
    0.90
     verdaderamente
    0.88
     veramente
    0.88
     wirklich
    0.88
    Activations Density 0.351%

    No Known Activations