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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15081
    Prev
    Next
    INDEX
    Explanations

    references to "bundle" or "Bundles" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.84
    httphttps
    -0.81
    getWriter
    -0.78
     Gough
    -0.71
     MotionEvent
    -0.71
     Wör
    -0.68
    /**
    -0.68
     GenerationType
    -0.66
    <<"\
    -0.66
    /**
    
    -0.66
    POSITIVE LOGITS
     bundle
    1.66
     Bundle
    1.56
     bundles
    1.54
    Bundle
    1.54
    bundle
    1.52
    bundles
    1.45
    UNDLE
    1.35
     Bund
    1.31
    Bundles
    1.30
    undle
    1.04
    Activations Density 0.008%

    No Known Activations