© 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. 7-GEMMASCOPE-RES-16K
    11. 15686
    Prev
    Next
    INDEX
    Explanations

    key concepts related to education and legal rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubo
    -0.45
    uring
    -0.42
     تعدى
    -0.41
     Grenz
    -0.40
     Administrativna
    -0.39
     dead
    -0.39
     Cary
    -0.39
     her
    -0.38
     misguided
    -0.38
    az
    -0.37
    POSITIVE LOGITS
     juſ
    0.66
     faſt
    0.63
     pleaſure
    0.62
    findpost
    0.57
     myſelf
    0.54
     Jefus
    0.52
     anſ
    0.52
    NameInMap
    0.51
     reaſon
    0.50
     poffe
    0.49
    Activations Density 0.535%

    No Known Activations