© 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. 10720
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions, particularly involving inequalities and sets

    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
    ządu
    -0.49
    AccessFile
    -0.47
    hdfs
    -0.46
    <eos>
    -0.45
     /**
    -0.45
     vệ
    -0.41
     elé
    -0.41
     Cleveland
    -0.41
    mongodb
    -0.41
     nozze
    -0.40
    POSITIVE LOGITS
    abestanden
    0.89
    HtmlAttribute
    0.79
    цездатний
    0.77
    basicConfig
    0.76
     Chwiliwch
    0.75
    WithIOException
    0.74
    rungsseite
    0.73
    andExpect
    0.71
     gyhoeddwyd
    0.71
     незавершена
    0.71
    Activations Density 0.862%

    No Known Activations