© 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. 6-GEMMASCOPE-RES-16K
    11. 2704
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formatted alignments in scientific or technical texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Duff
    -0.51
     ör
    -0.46
     oeufs
    -0.46
    wahati
    -0.45
    šinou
    -0.44
     Polres
    -0.43
    mom
    -0.42
     отдела
    -0.42
    MainPage
    -0.41
     аллер
    -0.41
    POSITIVE LOGITS
    aligned
    1.41
     myſelf
    1.07
     purpoſe
    1.04
     greateſt
    0.99
     ſeveral
    0.99
     pleaſure
    0.97
    存于互联网档案馆
    0.90
     ſtate
    0.89
     juſ
    0.89
     aligned
    0.88
    Activations Density 0.032%

    No Known Activations