© 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. 23-GEMMASCOPE-RES-16K
    11. 8515
    Prev
    Next
    INDEX
    Explanations

    descriptive accolades and evaluations of individuals, particularly in relation to their perceived qualities and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.39
    它
    -0.38
     svě
    -0.38
     vhodné
    -0.38
    它是
    -0.37
     它
    -0.36
    始まる
    -0.36
     apply
    -0.36
    heure
    -0.36
     giriş
    -0.36
    POSITIVE LOGITS
     himself
    0.67
    Personensuche
    0.59
    MLLoader
    0.57
    himself
    0.57
    parsedMessage
    0.57
     whom
    0.57
    Personendaten
    0.56
     himſelf
    0.54
     interviewed
    0.53
    encodeWith
    0.51
    Activations Density 0.392%

    No Known Activations