© 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. 41-GEMMASCOPE-RES-16K
    11. 5040
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and changes in life circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.55
    tagHelperRunner
    -0.51
    fortawesome
    -0.50
    Портал
    -0.48
    ]=>
    -0.48
     autorytatywna
    -0.47
    pushFollow
    -0.47
    RectangleBorder
    -0.46
    Filmographie
    -0.46
     NSCoder
    -0.44
    POSITIVE LOGITS
     probably
    3.08
    probably
    2.66
     possibly
    2.56
     likely
    2.55
     Probably
    2.53
     perhaps
    2.47
    Probably
    2.47
     probablemente
    2.45
     probabilmente
    2.38
     probablement
    2.31
    Activations Density 1.765%

    No Known Activations