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. 20-GEMMASCOPE-RES-16K
    6. 12021
    Prev
    Next
    INDEX
    Explanations

    terms associated with environmental conditions and community issues related to waste management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows prepositions expressing location/removal

    np_acts-logits-general · gemini-2.0-flash

    residential areas and neighbors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.67
    AddTagHelper
    -0.66
    AndEndTag
    -0.62
     milliards
    -0.61
    ViewImports
    -0.59
    Bissau
    -0.58
    transQ
    -0.56
     uș
    -0.56
     invokingState
    -0.54
    UnsafeEnabled
    -0.54
    POSITIVE LOGITS
     neighbors
    1.30
     residents
    1.29
    Residents
    1.19
     neighbours
    1.16
     homeowners
    1.15
     vecinos
    1.13
     Residents
    1.13
     neighbor
    1.12
     neighborhood
    1.11
     Neighbors
    1.10
    Activations Density 0.304%

    No Known Activations