© 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. 9584
    Prev
    Next
    INDEX
    Explanations

    concepts related to ideal or optimal conditions and scenarios

    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
    ={()=>
    -0.66
     –
    -0.65
    –
    -0.64
     Unab
    -0.64
    (()=>{
    -0.63
    ’
    -0.63
    …………………………………………
    -0.63
    fraid
    -0.61
    fcntl
    -0.61
    pac
    -0.60
    POSITIVE LOGITS
     Desired
    1.54
    desired
    1.51
     desired
    1.50
    desire
    1.44
     desires
    1.43
     Desire
    1.42
     desire
    1.39
     desirable
    1.38
    Desire
    1.36
     desirability
    1.31
    Activations Density 0.103%

    No Known Activations