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. 8-GEMMASCOPE-RES-16K
    6. 10590
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement and police

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nois
    -0.48
     صوتيه
    -0.48
    NOPQRST
    -0.48
     continents
    -0.48
    apor
    -0.47
    llus
    -0.47
    boa
    -0.44
    Anlage
    -0.44
     planta
    -0.43
    Xna
    -0.43
    POSITIVE LOGITS
     police
    1.16
     sheriff
    1.15
     Police
    1.12
     cops
    1.07
     RCMP
    1.06
    Police
    1.04
     Sheriff
    1.04
     POLICE
    1.03
    police
    1.00
    abinieri
    1.00
    Activations Density 0.233%

    No Known Activations