© 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. 12545
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and conditions, particularly those involving the cardiovascular system

    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
    tahankan
    -0.51
    StoryboardSegue
    -0.49
    appré
    -0.49
     porcentual
    -0.48
     percep
    -0.48
    Einzelnachweise
    -0.48
     percepción
    -0.45
     percentage
    -0.45
     perception
    -0.44
    percentage
    -0.44
    POSITIVE LOGITS
     diem
    0.51
     annum
    0.50
    المكان
    0.43
    ussis
    0.41
    ontal
    0.40
    ultimate
    0.40
    fect
    0.38
     ongel
    0.38
     storm
    0.38
    adaptiveStyles
    0.38
    Activations Density 0.261%

    No Known Activations