© 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. 1718
    Prev
    Next
    INDEX
    Explanations

    the occurrence of mathematical expressions and operations represented by "left" and "right" symbols, indicating their alignment in equations

    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
     чесно
    -0.69
    ways
    -0.66
     يتيمه
    -0.61
     transfieras
    -0.60
     Giles
    -0.58
    ########.
    -0.57
    他才
    -0.57
     cevap
    -0.57
     passage
    -0.57
    abat
    -0.55
    POSITIVE LOGITS
    left
    1.73
     left
    1.00
    Left
    0.93
     laiss
    0.92
    LEFT
    0.92
     laissé
    0.88
     محفوظة
    0.88
     myſelf
    0.88
     âgé
    0.88
     esquerdo
    0.85
    Activations Density 0.123%

    No Known Activations