© 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. 15-GEMMASCOPE-RES-16K
    11. 1911
    Prev
    Next
    INDEX
    Explanations

    the word "and" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    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
    -0.92
     Efq
    -0.89
     Jefus
    -0.86
     Majefty
    -0.85
     purpoſe
    -0.85
     himſelf
    -0.84
    ſelf
    -0.84
     fubject
    -0.83
     poffe
    -0.80
     poffible
    -0.79
    POSITIVE LOGITS
     And
    1.28
    Và
    1.23
    And
    1.13
    AND
    1.12
     AND
    1.11
    and
    0.96
    그리고
    0.91
     và
    0.86
    +"&
    0.85
    \&
    0.84
    Activations Density 0.240%

    No Known Activations