© 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. 3-GEMMASCOPE-RES-16K
    11. 9972
    Prev
    Next
    INDEX
    Explanations

    phrases related to temptation or coercion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringRunner
    -0.64
    atemala
    -0.58
    jsdelivr
    -0.56
    phère
    -0.56
    mannian
    -0.54
    issage
    -0.53
    lemented
    -0.53
    ALLENG
    -0.53
    selig
    -0.53
     DataLoader
    -0.53
    POSITIVE LOGITS
     resourceCulture
    0.63
    numerusform
    0.61
     AssemblyCompany
    0.61
     المعيارى
    0.56
     فريبيس
    0.56
     PeEnEo
    0.54
    Enllaces
    0.51
    InitVars
    0.50
    AutoresizingMask
    0.49
    XMLSchema
    0.48
    Activations Density 0.259%

    No Known Activations