© 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. 20-GEMMASCOPE-RES-16K
    11. 8487
    Prev
    Next
    INDEX
    Explanations

    terms related to diplomatic and governmental statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Statements, opinions, or expressions of condemnation

    np_acts-logits-general · gemini-2.0-flash

    expressed opinions or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المكان
    -0.61
    PyExc
    -0.61
     Ums
    -0.55
    casus
    -0.53
     فريبيس
    -0.53
     referenties
    -0.52
     supposedly
    -0.50
    OWN
    -0.49
     schein
    -0.49
    libur
    -0.48
    POSITIVE LOGITS
     condemned
    1.01
     condemn
    0.95
     condemns
    0.94
     Condem
    0.94
     commended
    0.92
     stressing
    0.91
     condemning
    0.89
     expressed
    0.88
     applauded
    0.86
     stressed
    0.84
    Activations Density 0.213%

    No Known Activations