© 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. 1-GEMMASCOPE-RES-16K
    11. 11177
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions or processes within scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.90
    RegressionTest
    -0.82
    setVerticalGroup
    -0.78
     Савезне
    -0.77
     CreateTagHelper
    -0.77
    IsContent
    -0.76
    enderror
    -0.73
    цезда
    -0.73
    estacks
    -0.71
     Administrativna
    -0.69
    POSITIVE LOGITS
     îns
    0.49
    ParallelGroup
    0.48
     через
    0.47
     camicia
    0.47
     vogliono
    0.47
    </em>
    0.45
     îi
    0.45
    0.44
     několika
    0.44
     ganhou
    0.42
    Activations Density 0.927%
    No Known Activations