© 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. 15-GEMMASCOPE-RES-16K
    11. 4365
    Prev
    Next
    INDEX
    Explanations

    expressions of boldness, bravery, and audacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.44
     dø
    -0.43
    #+#
    -0.42
    帖最后由
    -0.41
    ksana
    -0.38
    NetworkInfo
    -0.37
     perpetually
    -0.35
     trouverez
    -0.35
    wra
    -0.34
    xase
    -0.34
    POSITIVE LOGITS
     daring
    1.30
     bold
    1.19
    大胆
    1.16
     boldly
    1.16
     dares
    1.12
     berani
    1.12
     dared
    1.09
     Bold
    1.06
    Bold
    1.05
     dare
    1.05
    Activations Density 0.314%

    No Known Activations