© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4758
    Prev
    Next
    INDEX
    Explanations

    official declarations and electoral results in political contexts

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

    political news and events involving elections, government officials, and international relations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    非常的
    -0.56
    这件事情
    -0.50
     veramente
    -0.50
     idag
    -0.50
     maravillosa
    -0.49
     berdua
    -0.49
    følgelig
    -0.49
     verdaderamente
    -0.47
     tatouage
    -0.47
     disini
    -0.47
    POSITIVE LOGITS
    ніципалі
    0.54
    Britain
    0.49
    intellij
    0.46
     watchdog
    0.45
    stdc
    0.44
    amid
    0.44
     policymakers
    0.43
    featureID
    0.43
    Critics
    0.42
    tagHelperRunner
    0.42
    Activations Density 0.360%

    No Known Activations