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. 5-GEMMASCOPE-RES-16K
    6. 11339
    Prev
    Next
    INDEX
    Explanations

    phrases that express summarization or encapsulation of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lanjut
    -0.52
     allAfrica
    -0.51
     installé
    -0.48
    seiti
    -0.48
    };*/
    -0.48
     attiva
    -0.47
    VIAF
    -0.47
     planted
    -0.46
     görüş
    -0.45
     anteced
    -0.45
    POSITIVE LOGITS
     conveys
    1.00
     captures
    0.96
     convey
    0.90
     capturing
    0.87
     conveying
    0.86
    XmlAccessorType
    0.83
     mewakili
    0.82
     summarise
    0.82
     encaps
    0.82
    captures
    0.81
    Activations Density 0.257%

    No Known Activations