© 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. 9360
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to medical conditions and research discussions

    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
    +#+#
    -0.83
     nakalista
    -0.82
    +#+
    -0.80
    writeFieldEnd
    -0.79
     gynhyrchwyd
    -0.75
    OGND
    -0.75
    󠁴
    -0.75
     AssemblyCulture
    -0.74
     مرئيه
    -0.69
     виправивши
    -0.68
    POSITIVE LOGITS
    uxxxx
    1.55
    weightedMode
    0.62
    InjectAttribute
    0.58
    InstrumentedTest
    0.52
     MemoryStream
    0.45
     vaisselle
    0.36
     cálido
    0.34
     ríos
    0.34
     editText
    0.33
     kesi
    0.32
    Activations Density 1.710%

    No Known Activations