Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4453
    Prev
    Next
    INDEX
    Explanations

    terms related to power dynamics and political control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kla
    -0.58
     Kanto
    -0.56
     Lithuanian
    -0.52
     Sikkim
    -0.50
    mayacak
    -0.49
    Kla
    -0.49
     Lithuania
    -0.48
    Idaho
    -0.48
     Odisha
    -0.47
     Laus
    -0.46
    POSITIVE LOGITS
     Arabic
    1.59
     Islamic
    1.55
     Muslim
    1.48
     Arab
    1.48
     Islam
    1.46
     Arabs
    1.39
     Muslims
    1.39
    Islamic
    1.39
     Sheikh
    1.35
     Ramadan
    1.34
    Activations Density 2.604%

    No Known Activations