© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 7345
    Prev
    Next
    INDEX
    Explanations

    incidents of injury or harm occurring during various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouble
    -0.48
     gainera
    -0.45
    льше
    -0.44
    XmlElement
    -0.43
    jahres
    -0.43
    protobuf
    -0.41
    éfono
    -0.41
    انظر
    -0.41
    kube
    -0.40
    ubs
    -0.39
    POSITIVE LOGITS
    AnchorStyles
    0.90
     during
    0.83
    UrlResolution
    0.82
    during
    0.82
     للمعارف
    0.77
     أثناء
    0.75
     viewDidLoad
    0.74
    หว่าง
    0.73
     DURING
    0.71
     nahilalakip
    0.70
    Activations Density 0.307%

    No Known Activations