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 - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13754
    Prev
    Next
    INDEX
    Explanations

    references to the concept of universal or universalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.83
     <<<<<<<<<<<<<<
    -0.69
     vuitton
    -0.68
     nawr
    -0.67
    ⓘ
    -0.65
     Beecher
    -0.64
    ValueStyle
    -0.64
     IPO
    -0.64
     Numerology
    -0.64
     SwiftUI
    -0.64
    POSITIVE LOGITS
     Universal
    1.19
     sig
    1.15
     Sig
    1.09
    sig
    1.09
    Universal
    1.09
    Sig
    1.06
     universal
    1.00
    universal
    0.97
     UNIVERSAL
    0.94
    SIG
    0.84
    Activations Density 0.081%

    No Known Activations