© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1567
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial and operational performance metrics

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

    statements related to financial performance and future projections

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

    future growth and expectations

    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
    stateProvider
    -0.58
    MarshalTo
    -0.58
    RegressionTest
    -0.56
    tellbar
    -0.56
     оригіналу
    -0.52
    osene
    -0.50
    irement
    -0.50
    isticated
    -0.50
    RegistryLite
    -0.49
    otis
    -0.49
    POSITIVE LOGITS
     ready
    1.13
     poised
    1.10
     slated
    1.00
     preparing
    0.99
     destined
    0.97
     scheduled
    0.95
     set
    0.93
     prepares
    0.93
     prepare
    0.91
    ready
    0.86
    Activations Density 0.165%

    No Known Activations