© 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. 35-GEMMASCOPE-RES-16K
    11. 10948
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes involving interactions with individuals from different backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apapun
    -0.59
     любых
    -0.56
     quaisquer
    -0.53
     tetap
    -0.52
     především
    -0.52
     przede
    -0.52
     любые
    -0.51
    ArrowToggle
    -0.50
     any
    -0.50
     anything
    -0.50
    POSITIVE LOGITS
     accidentally
    0.89
    たまたま
    0.80
     overheard
    0.76
     inadvertently
    0.73
     recently
    0.72
     случайно
    0.71
    某
    0.70
     visiting
    0.69
     someone
    0.68
    ふと
    0.68
    Activations Density 0.861%

    No Known Activations