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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 145
    Prev
    Next
    INDEX
    Explanations

    information related to nuclear energy production and its infrastructure

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

    technical specifications and performance metrics related to machinery

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

    power output

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     AssemblyCulture
    -0.58
     prolongation
    -0.55
    eloma
    -0.53
     lengthening
    -0.52
     InputDecoration
    -0.52
    Hrsg
    -0.51
     lengthen
    -0.51
    selaer
    -0.50
    Edited
    -0.49
     prega
    -0.48
    POSITIVE LOGITS
     power
    1.32
    power
    1.23
     powers
    1.14
     Power
    1.12
    Power
    1.11
    powers
    1.09
     POWER
    1.08
     puissance
    1.08
    POWER
    1.08
     wattage
    1.04
    Activations Density 0.096%

    No Known Activations