© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3038
    Prev
    Next
    INDEX
    Explanations

    historical dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.61
    AddTagHelper
    -0.57
     Monfieur
    -0.57
    flashdata
    -0.57
     myſelf
    -0.55
     Verſ
    -0.53
     ſte
    -0.52
    клопе
    -0.49
     houſe
    -0.48
     transf
    -0.48
    POSITIVE LOGITS
     AD
    1.31
     BC
    1.07
    AD
    1.05
     CE
    0.98
    BC
    0.86
     BCE
    0.85
    CE
    0.78
     Anno
    0.68
    公元
    0.65
     AC
    0.63
    Activations Density 0.393%

    No Known Activations