© 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. 346
    Prev
    Next
    INDEX
    Explanations

    references to visual art or photography involving children

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

    Depictions of people, especially women and soldiers

    np_acts-logits-general · gemini-2.0-flash

    person holding object

    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
    دانشنامهٔ
    -0.79
     ویکی‌پدیا
    -0.78
     चीज़ों
    -0.78
     NSCoder
    -0.78
     Houſe
    -0.77
     propOrder
    -0.77
     houſe
    -0.75
    EndInit
    -0.74
     AssemblyCompany
    -0.74
     cauſe
    -0.72
    POSITIVE LOGITS
     pose
    0.93
     smiling
    0.83
     holding
    0.80
     standing
    0.79
     poses
    0.77
     posing
    0.76
     seated
    0.76
     wearing
    0.74
     posed
    0.74
     surrounded
    0.71
    Activations Density 0.192%

    No Known Activations