© 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. 4-GEMMASCOPE-RES-16K
    11. 2013
    Prev
    Next
    INDEX
    Explanations

    references to changes or alterations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kadang
    -0.53
     so
    -0.52
     us
    -0.51
    はる
    -0.50
     possession
    -0.49
     am
    -0.48
    什么
    -0.48
    czy
    -0.47
    ,
    -0.46
    supposed
    -0.46
    POSITIVE LOGITS
     changes
    1.62
     Changes
    1.52
    Changes
    1.47
    changes
    1.41
    CHANGES
    1.38
     CHANGES
    1.33
    MigrationBuilder
    1.19
     changements
    1.11
     alterations
    1.10
     Veränderungen
    1.06
    Activations Density 0.462%

    No Known Activations