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. 7-GEMMASCOPE-RES-16K
    6. 6360
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement officers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &=&
    -0.78
     Schmel
    -0.72
    TryParse
    -0.71
     kans
    -0.70
    Eben
    -0.69
    anical
    -0.68
    Spoljašnje
    -0.68
    gunaan
    -0.67
    Ẽ
    -0.66
     Bode
    -0.66
    POSITIVE LOGITS
     officers
    1.99
     Officers
    1.90
     Officer
    1.84
     OFFICER
    1.83
     officer
    1.79
    Officers
    1.78
    officer
    1.78
     OFFICERS
    1.76
    officers
    1.74
    Officer
    1.64
    Activations Density 0.040%

    No Known Activations