© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4456
    Prev
    Next
    INDEX
    Explanations

    words describing unsettling or alarming situations and emotions

    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
    Personendaten
    -0.47
    eseorang
    -0.42
     AssemblyCulture
    -0.42
    тьяна
    -0.41
     AssemblyVersion
    -0.41
    RTLR
    -0.39
    Portály
    -0.39
     يتيمه
    -0.38
    GHIJKLM
    -0.38
     siitä
    -0.38
    POSITIVE LOGITS
     frightening
    0.89
     impressive
    0.82
     alarming
    0.81
     horrifying
    0.79
     astonishing
    0.78
     terrifying
    0.77
     fascinating
    0.75
     intriguing
    0.75
     appealing
    0.75
     interesting
    0.75
    Activations Density 0.360%

    No Known Activations