© 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. 9994
    Prev
    Next
    INDEX
    Explanations

    terms related to habitat and ecosystem characteristics, particularly regarding anthropogenic effects and biodiversity

    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
    MLLoader
    -0.79
    WriteBarrier
    -0.66
    IntoConstraints
    -0.63
     препратки
    -0.61
     phenyl
    -0.60
    DoubleQuotes
    -0.57
    навли
    -0.56
     Wolfram
    -0.56
    StructEnd
    -0.56
     gelang
    -0.56
    POSITIVE LOGITS
     habitat
    1.83
     habitats
    1.64
    Habitat
    1.59
     Habitat
    1.58
    habitat
    1.55
     Habitats
    1.27
     biodiversity
    1.25
     wildlife
    1.14
     ecosystems
    1.09
     hábitat
    1.08
    Activations Density 0.162%

    No Known Activations