© 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. 9217
    Prev
    Next
    INDEX
    Explanations

    terms related to hosting and related entities in a networking or community context

    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
    er
    -0.54
    eaway
    -0.52
    LError
    -0.50
     getPage
    -0.50
    erals
    -0.50
    rachel
    -0.50
     telefonu
    -0.49
     sereia
    -0.48
     SqlConnection
    -0.47
    ENCIÓN
    -0.47
    POSITIVE LOGITS
    tist
    0.75
    rist
    0.74
     Bist
    0.69
    st
    0.67
    sts
    0.65
    tttt
    0.64
    tst
    0.63
    kst
    0.63
    ost
    0.62
     Trist
    0.62
    Activations Density 0.267%

    No Known Activations