Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65932
    Prev
    Next
    INDEX
    Explanations

    references to press secretaries and their statements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.59
    UserScript
    -0.58
     AssemblyVersion
    -0.55
    AndEndTag
    -0.54
     المعيارى
    -0.54
     Wikimedijinoj
    -0.50
    +:+
    -0.50
    AutoScaleMode
    -0.49
     فريبيس
    -0.48
    点此举报
    -0.47
    POSITIVE LOGITS
     spokesman
    1.13
     Spokes
    1.12
     spokesperson
    1.08
    Spo
    0.94
     spokeswoman
    0.89
     spokes
    0.88
    spo
    0.86
     portavoz
    0.79
     spokespersons
    0.78
     Spo
    0.68
    Activations Density 0.015%

    No Known Activations