© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10846
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to killing and murder

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

    killing

    np_acts-logits-general · gemini-2.0-flash

    kill or murder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    homonymie
    -0.94
     createState
    -0.73
    Према
    -0.71
    AccessorTable
    -0.69
    rungsseite
    -0.65
    出版年
    -0.62
    elemField
    -0.58
     Amigo
    -0.58
    CDATA
    -0.57
    [--
    -0.57
    POSITIVE LOGITS
     kill
    1.07
     kills
    0.95
     KILL
    0.94
     Kill
    0.92
    kill
    0.90
    Murder
    0.86
    kills
    0.85
     killing
    0.85
    KILL
    0.83
     murder
    0.83
    Activations Density 0.133%

    No Known Activations