© 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
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8176
    Prev
    Next
    INDEX
    Explanations

    references to political and social power dynamics, particularly involving authoritarianism and human rights issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.47
    وبر
    -0.47
     EClass
    -0.46
    couz
    -0.45
     NSCoder
    -0.44
    Inters
    -0.44
    Emp
    -0.43
     emp
    -0.43
    PMailer
    -0.43
    flink
    -0.43
    POSITIVE LOGITS
    новниш
    0.57
    verwijspagina
    0.50
     صوتيه
    0.47
     países
    0.47
     ब्रेकडाउन
    0.47
     nonUne
    0.45
     countries
    0.45
     kautta
    0.43
     tapaht
    0.43
    :✨
    0.42
    Activations Density 0.516%

    No Known Activations