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

    Neuronpedia

    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. 18-GEMMASCOPE-RES-16K
    11. 136
    Prev
    Next
    INDEX
    Explanations

    deviations of the verb "have" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following forms of "have" or "has"

    np_acts-logits-general · gemini-2.0-flash

    verb "to have"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.14
     betweenstory
    -1.12
     itſelf
    -1.10
     contextLoads
    -1.00
     myſelf
    -0.98
     poffible
    -0.98
     Chriftian
    -0.97
     themſelves
    -0.97
     Jefus
    -0.96
    tagHelperRunner
    -0.94
    POSITIVE LOGITS
     a
    1.47
     been
    1.42
     an
    1.25
     the
    1.14
     no
    1.00
     had
    0.96
     gotten
    0.94
     got
    0.91
     taken
    0.89
     some
    0.87
    Activations Density 0.313%

    No Known Activations