© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 40-GEMMASCOPE-RES-16K
    11. 4614
    Prev
    Next
    INDEX
    Explanations

    references to specific names and places associated with leadership and political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.49
    rawDesc
    -0.45
     NSC
    -0.45
    TypedDataSet
    -0.45
     Ns
    -0.44
     ns
    -0.43
     nahilalakip
    -0.43
     ngu
    -0.42
    writeFieldEnd
    -0.42
    SPATH
    -0.41
    POSITIVE LOGITS
    ene
    0.79
    INE
    0.78
    ine
    0.76
    Ine
    0.74
    ani
    0.74
    anie
    0.74
     Ine
    0.74
    une
    0.73
    ane
    0.73
    ENE
    0.71
    Activations Density 1.368%

    No Known Activations