© 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. 22-GEMMASCOPE-RES-16K
    11. 12138
    Prev
    Next
    INDEX
    Explanations

    references to specific items or concepts in the text, particularly using demonstrative pronouns

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

    "this is" or "this was" phrase

    np_acts-logits-general · gemini-2.0-flash

    this that is/was/can/should

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thereto
    -0.50
     therein
    -0.48
    BindView
    -0.47
    ธ์
    -0.45
    
    -0.45
     therewith
    -0.44
     most
    -0.44
    ≔
    -0.44
     uveden
    -0.43
     coste
    -0.42
    POSITIVE LOGITS
     שוליים
    1.02
     guy
    1.01
     stuff
    0.99
     shit
    0.85
     fucker
    0.82
     مشين
    0.77
     crap
    0.76
     motherfucker
    0.75
     StatelessWidget
    0.74
    玩意
    0.74
    Activations Density 0.269%

    No Known Activations