© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5457
    Prev
    Next
    INDEX
    Explanations

    references to criminal activities or heists in narratives

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

    Theft, robbery, and burglary

    np_acts-logits-general · gemini-2.0-flash

    armed robbery

    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
     MainAxisSize
    -0.60
    IHC
    -0.55
    NewUrlParser
    -0.55
     giras
    -0.54
     Correspondence
    -0.53
     fald
    -0.52
    UnitTesting
    -0.52
    HomeAsUpEnabled
    -0.52
    stums
    -0.51
    ]<<"
    -0.51
    POSITIVE LOGITS
     theft
    2.03
     stolen
    1.96
     thief
    1.94
     thieves
    1.92
     stealing
    1.89
     robbery
    1.86
     thefts
    1.85
     steal
    1.83
     Theft
    1.70
     stole
    1.66
    Activations Density 0.508%

    No Known Activations