© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6099
    Prev
    Next
    INDEX
    Explanations

    mentions of the government and its various roles or actions

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

    "government"

    np_acts-logits-general · gemini-2.0-flash

    government's role and actions

    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
     ✭✭
    -0.57
    drill
    -0.52
    curious
    -0.51
    ★☆
    -0.51
    başı
    -0.51
    MessageTagHelper
    -0.50
    HasIndex
    -0.50
    Geplaatst
    -0.48
    enderror
    -0.47
     SAMPLES
    -0.47
    POSITIVE LOGITS
     government
    1.95
     Government
    1.83
    Government
    1.71
    government
    1.70
     GOVERNMENT
    1.59
     govt
    1.48
     Govt
    1.48
    政府
    1.46
     gouvernement
    1.42
    GOVERNMENT
    1.42
    Activations Density 0.090%

    No Known Activations