© 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. 4-GEMMASCOPE-RES-16K
    11. 9800
    Prev
    Next
    INDEX
    Explanations

    phrases indicating occurrences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crdi
    -0.75
     cdti
    -0.69
     Shaksp
    -0.69
     Bioaccumulative
    -0.68
     متحده
    -0.67
     vainqueur
    -0.66
     miljoner
    -0.65
    цездатний
    -0.65
    writerow
    -0.64
     muerta
    -0.63
    POSITIVE LOGITS
     coincident
    1.15
     coinc
    1.03
     coincidence
    1.00
     coincide
    0.87
    剛好
    0.86
    刚好
    0.84
     incidentally
    0.83
    正好
    0.83
    たまたま
    0.81
     fortu
    0.78
    Activations Density 0.271%

    No Known Activations