© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11729
    Prev
    Next
    INDEX
    Explanations

    terminologies and references related to minerals, specifically ores

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

    ending in "ore" or "ure"

    np_acts-logits-general · gemini-2.0-flash

    ore, ure, and mare suffixes

    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
     jScrollPane
    -0.87
     Obrador
    -0.66
    日閲覧
    -0.66
    脚注の使い方
    -0.66
    ApiModelProperty
    -0.65
    Hochspringen
    -0.64
    yethylene
    -0.63
    rigation
    -0.63
    isations
    -0.63
    rician
    -0.62
    POSITIVE LOGITS
    Ere
    0.61
     sanitarias
    0.54
     gravedad
    0.51
     chrétienne
    0.49
    írito
    0.48
     Doreen
    0.47
    nder
    0.47
     HIR
    0.47
     przestr
    0.46
    ="#"><
    0.46
    Activations Density 0.182%

    No Known Activations