© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 12125
    Prev
    Next
    INDEX
    Explanations

    negation expressions in code logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.58
    5
    -0.57
    3
    -0.55
     x
    -0.55
    ↵↵
    -0.54
    7
    -0.54
    ’
    -0.53
      
    -0.53
    de
    -0.51
    <eos>
    -0.51
    POSITIVE LOGITS
    InjectAttribute
    1.14
    protoimpl
    1.02
     nahilalakip
    1.02
    (!__
    0.98
    IntoConstraints
    0.97
    AccessorTable
    0.96
    mybatisplus
    0.95
    GraphicsUnit
    0.94
     {!
    0.92
     epä
    0.92
    Activations Density 0.036%

    No Known Activations