© 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. 8814
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to combating or addressing serious social issues and threats

    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
    -0.67
    rungsseite
    -0.59
    лтемелер
    -0.56
    niña
    -0.55
     IndexPath
    -0.53
    parsedMessage
    -0.52
     GenerationType
    -0.51
     vuitton
    -0.51
    ьаж
    -0.50
    sidemargin
    -0.50
    POSITIVE LOGITS
    原始内容存档于
    0.56
     against
    0.49
     eliminating
    0.45
     illegal
    0.43
     eliminate
    0.43
     eliminates
    0.41
     prévenir
    0.36
    empêcher
    0.36
    illegal
    0.36
     excess
    0.36
    Activations Density 0.493%

    No Known Activations