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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15695
    Prev
    Next
    INDEX
    Explanations

    references to the action of retrieving text from fields or sources, particularly related to a charity context

    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
     ổn
    -0.62
    :✨
    -0.62
     Democrá
    -0.60
     Dispersion
    -0.58
    loys
    -0.57
     PRESENTATION
    -0.57
    WinForms
    -0.56
     Danilo
    -0.56
     Visita
    -0.55
     ڤ
    -0.55
    POSITIVE LOGITS
     charity
    1.42
    charity
    1.24
     charities
    1.18
    Charity
    1.07
     Charities
    1.02
     Charity
    0.99
     utility
    0.98
     Utility
    0.96
    NgModule
    0.95
     charitable
    0.89
    Activations Density 0.026%

    No Known Activations