Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15166
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their derivatives, particularly those containing 'thio' or related functional groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -1.22
    tonsoft
    -1.01
    ISupport
    -0.96
     Rodin
    -0.93
    SpringRunner
    -0.92
     GAG
    -0.90
     Tats
    -0.89
    PageFactory
    -0.89
     EClass
    -0.88
     rods
    -0.88
    POSITIVE LOGITS
     bou
    0.88
     Bou
    0.67
    omenclature
    0.66
     LOGGER
    0.65
     buk
    0.65
    ţional
    0.64
    Howdy
    0.62
     Keane
    0.61
     lon
    0.61
     anno
    0.60
    Activations Density 1.382%

    No Known Activations