© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8833
    Prev
    Next
    INDEX
    Explanations

    references to laws, restrictions, and regulations concerning social and political issues

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

    prohibitions and restrictions

    np_acts-logits-general · gemini-2.0-flash

    prohibited, banned, forbidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.54
    jarah
    -0.50
     underestimated
    -0.49
     المعيارى
    -0.49
    autorelease
    -0.48
    mặt
    -0.48
     Stretcher
    -0.47
     createSlice
    -0.46
     الرياضيه
    -0.46
     parallelogram
    -0.45
    POSITIVE LOGITS
     banned
    1.99
     prohibited
    1.92
     prohibition
    1.89
     forbidden
    1.86
     prohibitions
    1.85
     forbid
    1.81
     prohibit
    1.80
     prohibits
    1.72
     prohibiting
    1.72
     bans
    1.70
    Activations Density 0.487%

    No Known Activations