© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 12439
    Prev
    Next
    INDEX
    Explanations

    references to terrorist activities and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ssysteme
    -0.39
     kinerja
    -0.37
     helft
    -0.34
     Messung
    -0.33
     étages
    -0.33
     textStatus
    -0.32
     stappen
    -0.31
     floor
    -0.31
     बह
    -0.31
    latego
    -0.31
    POSITIVE LOGITS
     terrorist
    0.82
     terrorists
    0.81
     terrorism
    0.79
     guerrillas
    0.73
     extremist
    0.71
     terror
    0.69
     extremism
    0.67
    terror
    0.67
     extremists
    0.67
     guerrilla
    0.66
    Activations Density 0.457%

    No Known Activations