© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 551
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical actions and threats involving Russia and its leaders

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

    Russia and Putin

    np_acts-logits-general · gemini-2.0-flash

    Russia, Putin, Ukraine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     yh
    -0.49
     Jacobsen
    -0.44
     EconPapers
    -0.43
    encji
    -0.43
     interesado
    -0.42
     store
    -0.42
    шеб
    -0.41
    store
    -0.41
     fit
    -0.40
     tarvit
    -0.40
    POSITIVE LOGITS
    reportWebVitals
    0.49
     Kremlin
    0.46
     coö
    0.44
     russia
    0.43
     Putin
    0.43
    SpringRunner
    0.42
    MigrationBuilder
    0.42
    ponses
    0.42
    FieldBuilder
    0.41
     ©️
    0.40
    Activations Density 0.080%

    No Known Activations