© 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. 4-GEMMASCOPE-RES-16K
    11. 363
    Prev
    Next
    INDEX
    Explanations

    structured formatting elements, such as headers and code comment indicators

    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
     voren
    -0.61
     dė
    -0.60
    HomeAsUpEnabled
    -0.58
     kysy
    -0.58
    Namara
    -0.57
    timewa
    -0.57
     oculto
    -0.56
     oprot
    -0.55
     Teut
    -0.55
     medesimo
    -0.55
    POSITIVE LOGITS
     Pingback
    0.72
    sidemargin
    0.65
     ?>/
    0.58
    Aholisi
    0.54
    balleur
    0.52
     ExecuteAsync
    0.52
     ex
    0.52
     autorytatywna
    0.52
    лю
    0.51
    پیوند
    0.51
    Activations Density 0.096%

    No Known Activations