© 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. 10-GEMMASCOPE-RES-16K
    11. 12278
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating association or connection with other entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.63
     purpoſe
    -0.57
    ſelf
    -0.55
     Monfieur
    -0.55
     leſs
    -0.54
     reaſon
    -0.53
     lefs
    -0.53
    ſelves
    -0.51
     beſt
    -0.51
     fubject
    -0.51
    POSITIVE LOGITS
     plus
    0.93
     ditambah
    0.80
    plus
    0.80
    makeText
    0.80
     Plus
    0.80
     accompanying
    0.78
     accompagné
    0.76
     accompanied
    0.76
     плюс
    0.73
     +
    0.73
    Activations Density 0.265%

    No Known Activations