© 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. 25-GEMMASCOPE-RES-16K
    6. 1270
    Prev
    Next
    INDEX
    Explanations

    terms related to labor and employment rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctx
    -1.01
     ctx
    -0.98
    RuleContext
    -0.84
     Mathi
    -0.74
    Ctx
    -0.74
    ImageContext
    -0.74
     Drake
    -0.70
    Drake
    -0.68
     Jesse
    -0.67
     Khan
    -0.67
    POSITIVE LOGITS
     Milli
    0.87
    Milli
    0.87
     Packard
    0.87
    Packard
    0.84
     HP
    0.79
    HP
    0.67
     Ced
    0.67
     Giga
    0.66
     Archibald
    0.66
     centi
    0.64
    Activations Density 1.679%

    No Known Activations