© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 23
    Prev
    Next
    INDEX
    Explanations

    terms related to terrorism and counter-terrorism efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.50
    mybatisplus
    -0.45
     initComponents
    -0.40
    InjectAttribute
    -0.39
    Tikang
    -0.39
    WebElementEntity
    -0.39
    ://$
    -0.38
    良
    -0.37
     glabrous
    -0.37
    ScopeManager
    -0.37
    POSITIVE LOGITS
     terrorists
    0.79
     terrorist
    0.79
     terrorism
    0.73
     ISIS
    0.72
     Islamist
    0.65
    terrorism
    0.63
    terror
    0.63
    ISIS
    0.60
     mosques
    0.59
     extremism
    0.59
    Activations Density 0.194%

    No Known Activations