© 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. 3-GEMMASCOPE-RES-16K
    11. 13114
    Prev
    Next
    INDEX
    Explanations

    information related to healthcare and assistance for people with specific medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.77
     ModelExpression
    -0.76
    EndGlobalSection
    -0.71
     ujednoznacz
    -0.67
     CreateTagHelper
    -0.66
    ỡng
    -0.65
    queryInterface
    -0.64
    StructEnd
    -0.62
    BufferException
    -0.61
     <=",
    -0.60
    POSITIVE LOGITS
     Efq
    0.57
    }));
    0.55
    rafts
    0.54
     aprendido
    0.51
     vectorielle
    0.51
     Jefus
    0.50
     formales
    0.50
     myſelf
    0.49
     attiv
    0.48
    (&:
    0.48
    Activations Density 0.329%

    No Known Activations