© 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. 15-GEMMASCOPE-RES-16K
    11. 3688
    Prev
    Next
    INDEX
    Explanations

    concepts related to the chemical processes and compositions that involve sulfur and its compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اب
    -0.45
     rí
    -0.44
     sahip
    -0.44
     appuntamento
    -0.42
    ształ
    -0.42
    布
    -0.41
    ENSITY
    -0.41
    佈
    -0.40
    }{|
    -0.39
    чье
    -0.39
    POSITIVE LOGITS
     processes
    0.89
    processes
    0.84
     Processes
    0.83
     reactions
    0.79
    matchCondition
    0.78
     metabolism
    0.77
     Himo
    0.77
    Tikang
    0.75
    setVerticalGroup
    0.75
     process
    0.75
    Activations Density 1.229%

    No Known Activations