© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 7840
    Prev
    Next
    INDEX
    Explanations

    specific player names and game statistics in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.71
    XmlAccessType
    -0.65
    ThroughAttribute
    -0.61
    transQ
    -0.61
    Personendaten
    -0.59
     صوتيه
    -0.58
    GEBURTSDATUM
    -0.58
    ंदीखरीदारी
    -0.56
    ніципалі
    -0.55
     gwaran
    -0.55
    POSITIVE LOGITS
    исленность
    0.44
     Catawiki
    0.41
    يكب
    0.38
     pun
    0.33
    obald
    0.33
    glass
    0.33
     bench
    0.32
    fmt
    0.32
    BENCH
    0.32
    itní
    0.31
    Activations Density 0.259%

    No Known Activations