© 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. 3-GEMMASCOPE-RES-16K
    11. 5518
    Prev
    Next
    INDEX
    Explanations

    phrases indicating definitions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.78
     Monfieur
    -0.73
     raiſ
    -0.71
     myſelf
    -0.71
    +#+#
    -0.69
     itſelf
    -0.69
     ſche
    -0.68
     Eſ
    -0.68
     ſind
    -0.66
     pleaſure
    -0.65
    POSITIVE LOGITS
     means
    0.69
     meaning
    0.68
     के
    0.56
     Meaning
    0.54
     carrier
    0.49
     meanings
    0.48
    Meanwhile
    0.47
     mean
    0.46
    meaning
    0.45
     Means
    0.45
    Activations Density 0.087%

    No Known Activations