© 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. 11-GEMMASCOPE-RES-16K
    6. 6658
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to sustainability and sustainable practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انجليز
    -0.96
    bootstrapcdn
    -0.82
    !*\
    -0.77
     henvisninger
    -0.74
    PMailer
    -0.74
    ThroughAttribute
    -0.73
     وتسجيلات
    -0.72
     createSlice
    -0.71
     TextAppearance
    -0.71
     Childs
    -0.71
    POSITIVE LOGITS
     sustainable
    1.21
     Sustainable
    1.19
     sustainability
    1.15
     sustainably
    1.13
    ustainable
    1.11
     Sustain
    1.09
     Sust
    1.08
    Sustainable
    1.08
     unsustainable
    1.05
    sustainable
    1.03
    Activations Density 0.047%

    No Known Activations