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

    Neuronpedia

    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. 41-GEMMASCOPE-RES-16K
    11. 10636
    Prev
    Next
    INDEX
    Explanations

    HTML or programming-related tags and structural elements in a document

    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
    DrawerToggle
    -0.74
    QMetaType
    -0.73
    icitis
    -0.69
    ctional
    -0.67
     StringTokenizer
    -0.65
    hibited
    -0.65
     JpaRepository
    -0.65
    icken
    -0.65
    neous
    -0.64
    AxisAlignment
    -0.64
    POSITIVE LOGITS
    }{#
    0.27
     udaler
    0.27
    Portály
    0.25
     Construcción
    0.24
    didSet
    0.23
    onBackPressed
    0.23
     Ditto
    0.23
    roient
    0.23
    >\<^
    0.22
    XXIII
    0.22
    Activations Density 0.543%

    No Known Activations