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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 50681
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Stanley" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stanley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referrerpolicy
    -0.63
     resourceCulture
    -0.60
    脚注の使い方
    -0.55
     otomatig
    -0.53
    imageURL
    -0.50
    iastes
    -0.50
    
    -0.50
     jButton
    -0.49
    weep
    -0.49
    yakarta
    -0.49
    POSITIVE LOGITS
     Stan
    1.05
    Stan
    1.00
     Stanley
    0.94
    STAN
    0.90
    Stanley
    0.89
     STAN
    0.83
     Stanis
    0.82
     STANLEY
    0.81
     stan
    0.81
    stan
    0.81
    Activations Density 0.008%

    No Known Activations