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. 12-GEMMASCOPE-RES-16K
    6. 1101
    Prev
    Next
    INDEX
    Explanations

    phrases related to convenience and comfort, particularly in the context of online activities and study environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adə
    -0.62
    ISupport
    -0.59
    <bos>
    -0.55
    ipedi
    -0.55
    XmlAccessorType
    -0.53
    ")));
    
    -0.49
     NUKAT
    -0.49
     minOccurs
    -0.48
     GetEnumerator
    -0.47
    ցված
    -0.47
    POSITIVE LOGITS
    EndContext
    0.59
    enumi
    0.58
    раздо
    0.57
     locatie
    0.57
    Referències
    0.55
    endroit
    0.55
     فريبيس
    0.55
    devServer
    0.55
     exteriores
    0.55
     themſelves
    0.55
    Activations Density 0.253%

    No Known Activations