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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7890
    Prev
    Next
    INDEX
    Explanations

    mentions of relaxation and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.98
    enumii
    -0.95
    ChildScrollView
    -0.85
     مشين
    -0.84
     themſelves
    -0.84
    出版年
    -0.84
     Houſe
    -0.83
    ValueStyle
    -0.81
     ſche
    -0.81
     laſt
    -0.79
    POSITIVE LOGITS
     relaxing
    0.62
     ple
    0.54
    lb
    0.52
     relax
    0.51
    enterOuterAlt
    0.51
    Optional
    0.50
     experiment
    0.49
     til
    0.47
     ses
    0.46
     sec
    0.46
    Activations Density 0.132%

    No Known Activations