© 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. 5-GEMMASCOPE-RES-16K
    11. 15820
    Prev
    Next
    INDEX
    Explanations

    terms related to projections and visual representations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tett
    -0.52
    AGS
    -0.51
    upan
    -0.51
    Примечания
    -0.51
    ecuzione
    -0.49
    quinha
    -0.49
    tap
    -0.49
    EventListener
    -0.48
    колад
    -0.48
     dokun
    -0.48
    POSITIVE LOGITS
     projection
    2.00
     Projection
    1.80
     projections
    1.76
     projected
    1.72
    projection
    1.71
    Projection
    1.68
     projecting
    1.64
    projected
    1.60
     projector
    1.60
     Projected
    1.59
    Activations Density 0.288%

    No Known Activations