© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1745
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it" and related phrases indicating action or instruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -1.21
     itſelf
    -1.19
     Jefus
    -1.17
     Anſ
    -1.16
     Chriftian
    -1.15
     Reſ
    -1.10
     ſtate
    -1.10
    ſelf
    -1.08
     Theſe
    -1.03
     pleaſure
    -1.02
    POSITIVE LOGITS
     done
    0.55
    getOne
    0.54
    AutoField
    0.52
    endpush
    0.51
    fetchall
    0.50
     go
    0.48
    ˋ
    0.48
    doit
    0.47
    gefügt
    0.46
    ejs
    0.46
    Activations Density 0.097%

    No Known Activations