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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 11748
    Prev
    Next
    INDEX
    Explanations

    phrases related to structures and their coverings or protective features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.71
     FetchType
    -0.66
    endphp
    -0.65
     Seeder
    -0.64
    elemField
    -0.61
     CreateTagHelper
    -0.60
    ⓧ
    -0.59
     विश्वसनीयता
    -0.58
     Haig
    -0.57
     constipation
    -0.57
    POSITIVE LOGITS
     Shelter
    0.97
    Shelter
    0.93
     shelter
    0.93
     shelters
    0.88
    shelter
    0.82
    发表于
    0.74
     Shel
    0.69
     sheltered
    0.65
    Shel
    0.64
     Tent
    0.64
    Activations Density 0.113%

    No Known Activations