© 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. 9-GEMMASCOPE-RES-16K
    11. 10545
    Prev
    Next
    INDEX
    Explanations

    references to political repression and dissent

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

    Political activism and opposition

    np_acts-logits-general · gemini-2.0-flash

    pro-democracy activism and opposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tableFuture
    -0.52
    DockStyle
    -0.51
    MemoryWarning
    -0.47
    WriteBarrier
    -0.46
    StoryboardSegue
    -0.45
    ValueGenerated
    -0.44
    yntaxException
    -0.44
    moveToFirst
    -0.44
    XtraReports
    -0.43
     صوتيه
    -0.43
    POSITIVE LOGITS
     protester
    0.44
     Amnesty
    0.42
     opposition
    0.42
     torture
    0.40
     Protest
    0.40
     political
    0.39
     Opposition
    0.39
     Sewell
    0.38
     protest
    0.37
     authoritarian
    0.37
    Activations Density 0.331%

    No Known Activations