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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 5676
    Prev
    Next
    INDEX
    Explanations

    conjunctions that contrast or introduce exceptions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.56
    TResult
    -0.56
    ady
    -0.55
    즉
    -0.54
     Lage
    -0.51
    ame
    -0.49
    asm
    -0.49
    uman
    -0.48
    ComponentScan
    -0.47
     rangs
    -0.47
    POSITIVE LOGITS
    rawDesc
    0.86
     propOrder
    0.81
    OGND
    0.73
    Personensuche
    0.73
    তথ্যসূত্র
    0.72
     defStyleAttr
    0.71
     surla
    0.70
    RetentionPolicy
    0.68
    Datuak
    0.68
    featureID
    0.66
    Activations Density 0.265%

    No Known Activations