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. 16-GEMMASCOPE-RES-16K
    6. 5170
    Prev
    Next
    INDEX
    Explanations

    terms related to social and political systems, particularly focusing on immigration, healthcare, and environmental issues

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

    before types of policies or systems

    np_acts-logits-general · gemini-2.0-flash

    governance, policy, and societal issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tangentMode
    -0.62
    EDEFAULT
    -0.56
    ävän
    -0.56
    ABET
    -0.56
    ودی
    -0.54
    ScreenState
    -0.53
    PageRoute
    -0.51
     Brun
    -0.51
     outwardly
    -0.51
    WithMany
    -0.50
    POSITIVE LOGITS
    +#+#
    0.68
     matters
    0.62
    wpdb
    0.62
    tvguidetime
    0.60
     behavior
    0.60
     subsystem
    0.59
     system
    0.58
     policy
    0.57
     behaviour
    0.55
     reform
    0.55
    Activations Density 0.540%

    No Known Activations