© 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. 0-GEMMASCOPE-RES-16K
    11. 7047
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "him" and references to time, indicated by the repeated occurrence of the character for "year."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -1.60
     Roskov
    -1.41
     Efq
    -1.39
     itſelf
    -1.36
     Majefty
    -1.33
    ^(@)
    -1.27
     doubtnut
    -1.25
    CloseOperation
    -1.25
     Jefus
    -1.22
     Monfieur
    -1.18
    POSITIVE LOGITS
     him
    1.13
     us
    1.10
    him
    0.94
     me
    0.71
     to
    0.67
    us
    0.66
     them
    0.65
    年
    0.63
    Him
    0.62
    ,
    0.61
    Activations Density 0.359%

    No Known Activations