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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5188
    Prev
    Next
    INDEX
    Explanations

    terms related to marriage equality and discrimination against marginalized groups

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

    equal rights or equality

    np_acts-logits-general · gemini-2.0-flash

    equality and rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    []>
    -0.53
    pinas
    -0.47
     *>
    -0.46
     distraction
    -0.46
    afterEach
    -0.46
    guchi
    -0.46
    augh
    -0.46
     الداخلية
    -0.45
    افظ
    -0.45
     IBOutlet
    -0.45
    POSITIVE LOGITS
     rights
    1.72
    rights
    1.35
     equal
    1.32
     RIGHTS
    1.32
     equality
    1.32
     Rights
    1.31
     droits
    1.21
    Rights
    1.18
     Equal
    1.14
     diritti
    1.13
    Activations Density 0.486%

    No Known Activations