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. 25-GEMMASCOPE-RES-16K
    6. 12546
    Prev
    Next
    INDEX
    Explanations

    phrases that express criticism or comment on statements related to immigration

    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
    Демографія
    -0.75
     thru
    -0.71
     rumor
    -0.70
    Respectfully
    -0.67
    PerformLayout
    -0.67
     Utilizing
    -0.66
    utilized
    -0.66
     Recognize
    -0.66
     acá
    -0.65
    SuspendLayout
    -0.65
    POSITIVE LOGITS
     bosses
    0.85
    Organiser
    0.74
    Cllr
    0.70
     £
    0.68
     Cllr
    0.67
    Councillor
    0.67
    Labour
    0.65
    Speaking
    0.62
     Organiser
    0.61
     Labour
    0.61
    Activations Density 0.079%

    No Known Activations