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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10341
    Prev
    Next
    INDEX
    Explanations

    references to hostage situations or captivity

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

    Kidnapping, captivity, and prisoners

    np_acts-logits-general · gemini-2.0-flash

    hostages and prisoners

    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
    ArgsConstructor
    -0.48
    cimientos
    -0.47
     الحره
    -0.47
     policing
    -0.46
     للمعارف
    -0.46
    Autowired
    -0.44
     voisins
    -0.43
    رشف
    -0.41
     Jérusalem
    -0.41
     coefficient
    -0.40
    POSITIVE LOGITS
     hostage
    1.45
     hostages
    1.39
     captivity
    1.32
     captives
    1.24
     ransom
    1.24
     captive
    1.22
     kidnapped
    1.19
     abducted
    1.05
     prisoner
    1.04
     rescued
    1.04
    Activations Density 0.210%

    No Known Activations