© 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. 34-GEMMASCOPE-RES-16K
    11. 10774
    Prev
    Next
    INDEX
    Explanations

    instances of strong declarative statements or conclusions in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пожалуйста
    -0.52
    为止
    -0.52
    こいつ
    -0.49
     Vergnügen
    -0.48
    featureID
    -0.48
    numerusform
    -0.46
    ándalo
    -0.44
    这家伙
    -0.43
    kenstock
    -0.43
    颼
    -0.43
    POSITIVE LOGITS
     referring
    0.86
     Asked
    0.85
     Referring
    0.84
    Referring
    0.83
    Asked
    0.82
     pointing
    0.73
     citing
    0.72
     noting
    0.71
     Descri
    0.69
     speaking
    0.67
    Activations Density 0.306%

    No Known Activations