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

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29914
    Prev
    Next
    INDEX
    Explanations

    common Portuguese grammatical articles and prepositions

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

    O [word]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.52
     itſelf
    -1.51
     myſelf
    -1.49
     Reſ
    -1.48
     Houſe
    -1.45
     houſe
    -1.41
     pleaſure
    -1.38
     Anſ
    -1.36
     faſt
    -1.36
     ―――――
    -1.35
    POSITIVE LOGITS
     m
    0.82
     O
    0.73
     h
    0.72
     M
    0.71
     C
    0.71
     K
    0.68
     S
    0.66
     n
    0.65
     F
    0.65
     I
    0.64
    Activations Density 0.009%

    No Known Activations