Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5866
    Prev
    Next
    INDEX
    Explanations

    words related to theft and robbery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Correspondence
    -0.54
     giras
    -0.54
    Tembelea
    -0.50
    verso
    -0.48
    IHC
    -0.48
    vestream
    -0.47
    kazy
    -0.47
    lacable
    -0.47
    Correspondence
    -0.45
     MainAxisSize
    -0.45
    POSITIVE LOGITS
     stolen
    2.01
     theft
    2.00
     thief
    1.94
     stealing
    1.94
     thieves
    1.88
     steal
    1.87
     robbery
    1.85
     thefts
    1.83
     stole
    1.73
     steals
    1.67
    Activations Density 0.441%

    No Known Activations