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. 95
    Prev
    Next
    INDEX
    Explanations

    equality and comparison operators in code

    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
     gran
    -0.57
     tra
    -0.52
     Batch
    -0.52
    ALLOC
    -0.50
     о
    -0.50
     in
    -0.50
     fat
    -0.48
     batch
    -0.47
     droit
    -0.46
     St
    -0.46
    POSITIVE LOGITS
    ]==
    1.24
    ==
    1.05
    )==
    1.05
     itſelf
    1.05
     ==
    0.98
     Jefus
    0.97
     Shakspeare
    0.97
    =="
    0.96
     themſelves
    0.95
     raiſ
    0.95
    Activations Density 0.129%

    No Known Activations