© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15417
    Prev
    Next
    INDEX
    Explanations

    phrases related to issues of compliance and legal violations

    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
    complexContent
    -0.86
     propOrder
    -0.72
    NewUrlParser
    -0.70
    WriteAttribute
    -0.64
     JAXBElement
    -0.62
     getItemId
    -0.60
    Poloha
    -0.58
    memoized
    -0.57
    EndInit
    -0.57
     оригіналу
    -0.57
    POSITIVE LOGITS
     violation
    1.80
     violate
    1.65
     violations
    1.64
     violating
    1.59
     violates
    1.54
     violated
    1.48
     Violation
    1.46
     illegally
    1.39
    viol
    1.33
    violation
    1.33
    Activations Density 0.978%

    No Known Activations