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. 11-GEMMASCOPE-RES-16K
    6. 13785
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Linq
    -0.80
     frattempo
    -0.72
     Katal
    -0.71
    glicher
    -0.70
    <()>
    -0.69
     podido
    -0.67
     Mog
    -0.66
     Burnt
    -0.66
    Toler
    -0.64
    place
    -0.64
    POSITIVE LOGITS
     officers
    1.28
    officers
    1.25
     OFFICERS
    1.23
     Officers
    1.22
     OFFICER
    1.17
    Officers
    1.16
    officer
    1.13
     instruments
    1.10
     Instruments
    1.08
     Officer
    1.07
    Activations Density 0.102%

    No Known Activations