© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1871
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds and compositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -1.07
     وتسجيلات
    -0.86
     Jefus
    -0.86
     ſche
    -0.84
     Monfieur
    -0.84
     poffe
    -0.82
     ſp
    -0.81
     ſee
    -0.81
     Efq
    -0.80
     uſed
    -0.80
    POSITIVE LOGITS
    ath
    1.99
    th
    1.90
    TH
    1.81
    ATH
    1.75
    ith
    1.72
     TH
    1.68
    Th
    1.65
     Th
    1.65
    uth
    1.62
    थ
    1.61
    Activations Density 0.358%

    No Known Activations