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. 1-GEMMASCOPE-RES-16K
    6. 13832
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with terror and terrorism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.72
    :✨
    -0.65
    EndProject
    -0.64
    헌
    -0.62
    EndContext
    -0.61
     CWE
    -0.60
    вар
    -0.59
    XmlAccessType
    -0.59
     gyhoeddwyd
    -0.57
     requestCode
    -0.56
    POSITIVE LOGITS
    Terror
    1.39
     terror
    1.38
     Terror
    1.36
    terror
    1.32
     terrorism
    1.21
     terrorists
    1.19
     terrorist
    1.18
    terrorism
    1.03
     Terrorism
    1.01
     tennis
    0.90
    Activations Density 0.045%

    No Known Activations