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. 22-GEMMASCOPE-RES-16K
    6. 10948
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights and referendums concerning autonomy and governance

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

    national identity or separation

    np_acts-logits-general · gemini-2.0-flash

    territorial status and independence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Synagogue
    -0.49
     Turquie
    -0.47
    ்த்த
    -0.47
    apyrus
    -0.47
    windowFixed
    -0.47
     asiatique
    -0.47
     Manson
    -0.47
     Grosvenor
    -0.46
    HasIndex
    -0.46
     Infection
    -0.45
    POSITIVE LOGITS
     independence
    1.13
     autonomy
    1.02
     sovereignty
    0.97
    independence
    0.96
     independent
    0.89
     autonomous
    0.85
     Autonomy
    0.84
    Independence
    0.83
     Independence
    0.83
     separ
    0.81
    Activations Density 0.535%

    No Known Activations