© 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. 24-GEMMASCOPE-RES-16K
    11. 9259
    Prev
    Next
    INDEX
    Explanations

    references to targeting individuals or groups, especially in a political or social context

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

    before/after "target," "prey," or "victim."

    np_acts-logits-general · gemini-2.0-flash

    targets, victims, or prey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.66
    RegressionTest
    -0.57
    extrême
    -0.56
    Hochspringen
    -0.50
     /\.(
    -0.49
     للمعارف
    -0.48
     montée
    -0.47
    GeneratedMessage
    -0.47
    êng
    -0.45
     CascadeType
    -0.45
    POSITIVE LOGITS
     targets
    1.43
     target
    1.35
     prey
    1.32
     victims
    1.24
     victim
    1.21
    targets
    1.18
    target
    1.15
    Targets
    1.12
     Targets
    1.10
    prey
    1.01
    Activations Density 0.321%

    No Known Activations