© 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. 8484
    Prev
    Next
    INDEX
    Explanations

    nested structures or classifications within a document

    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
     itſelf
    -2.86
     myſelf
    -2.65
     Monfieur
    -2.56
     Efq
    -2.51
     ―――――
    -2.44
     themſelves
    -2.31
     raiſ
    -2.31
     Majefty
    -2.30
     Houſe
    -2.26
     himſelf
    -2.26
    POSITIVE LOGITS
     
    1.55
    ,
    1.42
     in
    1.39
    .
    1.33
    -
    1.30
     a
    1.29
     and
    1.29
     the
    1.24
     I
    1.23
     for
    1.22
    Activations Density 0.661%

    No Known Activations