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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14835
    Prev
    Next
    INDEX
    Explanations

    words related to sanctions or punitive measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onViewCreated
    -0.68
    enumi
    -0.66
    StoryboardSegue
    -0.61
    localtime
    -0.60
    ynchronously
    -0.57
     Wiktionnaire
    -0.56
    greSQL
    -0.55
    abestanden
    -0.55
    ACKNOWLEDGEMENT
    -0.54
    usermodel
    -0.54
    POSITIVE LOGITS
     restrictions
    1.81
     restriction
    1.78
     ban
    1.67
     bans
    1.63
     banning
    1.56
     Restrictions
    1.52
     restrictive
    1.47
     restric
    1.47
     prohibition
    1.46
     Restriction
    1.45
    Activations Density 0.512%

    No Known Activations