Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 7126
    Prev
    Next
    INDEX
    Explanations

    terms related to international sanctions, particularly focused on Russia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.70
    tenham
    -0.67
    endphp
    -0.62
     الرياضيه
    -0.60
    AnchorTagHelper
    -0.59
    mapStateToProps
    -0.58
    ISupport
    -0.58
     autorytatywna
    -0.57
     الحره
    -0.56
     🙂
    -0.56
    POSITIVE LOGITS
     allegedly
    0.84
     supuestamente
    0.80
     deemed
    0.77
     jugé
    0.67
     pursuant
    0.67
     controversi
    0.66
     indefinitely
    0.65
     supposedly
    0.65
     unilaterally
    0.64
     conformément
    0.64
    Activations Density 0.728%

    No Known Activations