© 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. 10514
    Prev
    Next
    INDEX
    Explanations

    names, titles, and entities related to specific individuals or organizations

    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
    yntaxException
    -0.25
     bArr
    -0.24
    <bos>
    -0.24
     lyk
    -0.22
    ksp
    -0.21
     rhod
    -0.20
    extAlignment
    -0.20
     تضيفلها
    -0.20
    gebob
    -0.19
     stihl
    -0.19
    POSITIVE LOGITS
     Spanish
    0.73
     Grupo
    0.72
     Universidad
    0.70
     Instituto
    0.68
     Escuela
    0.67
     Ciudad
    0.67
     Puerto
    0.67
     María
    0.66
     Palacio
    0.65
    Spanish
    0.65
    Activations Density 18.884%

    No Known Activations