© 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. 4-GEMMASCOPE-RES-16K
    11. 1209
    Prev
    Next
    INDEX
    Explanations

    terms related to background noise and performance metrics in experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.67
     خارجية
    -0.66
    URLException
    -0.60
    évaluateur
    -0.58
     Rtl
    -0.58
     Ráp
    -0.57
     persil
    -0.57
    ℗
    -0.57
    FormTagHelper
    -0.56
    ValueStyle
    -0.55
    POSITIVE LOGITS
     idle
    0.84
    idle
    0.78
     Idle
    0.67
    Idle
    0.66
     filler
    0.64
     overhead
    0.64
     passive
    0.60
     inert
    0.60
     idly
    0.59
    filler
    0.58
    Activations Density 2.585%

    No Known Activations