© 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. 3-GEMMASCOPE-RES-16K
    11. 16038
    Prev
    Next
    INDEX
    Explanations

    keywords related to nature, parks, and conservation in text

    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
     ProtoMessage
    -0.89
     AssemblyTitle
    -0.85
    WithIOException
    -0.80
    tanleria
    -0.80
     ivelany
    -0.79
    تقاوى
    -0.78
    __":
    -0.72
    AddTagHelper
    -0.71
    gentes
    -0.70
     téléphonique
    -0.69
    POSITIVE LOGITS
     wildlife
    0.70
     heritage
    0.58
     WILDLIFE
    0.57
     Heritage
    0.56
     Wildlife
    0.55
    Wildlife
    0.54
    примеча
    0.54
    Heritage
    0.54
    heritage
    0.54
     Naturs
    0.53
    Activations Density 0.644%

    No Known Activations