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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4474
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions of characteristics or qualities in various contexts

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

    after common punctuation

    np_acts-logits-general · gemini-2.0-flash

    hope discussion, legal sentencing, owner recalls

    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
    jspx
    -0.68
     ​​
    -0.59
    RenderAtEndOf
    -0.50
    migrationBuilder
    -0.49
    &__
    -0.48
     i
    -0.45
    onte
    -0.45
     שלו
    -0.44
    IContainer
    -0.44
    phorus
    -0.43
    POSITIVE LOGITS
    帖最后由
    0.79
     houſe
    0.76
     pleaſure
    0.73
     LIRE
    0.72
    šanai
    0.71
     purpoſe
    0.69
     Arquivado
    0.68
     ſta
    0.67
     Monfieur
    0.67
     faſt
    0.67
    Activations Density 1.001%

    No Known Activations