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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6014
    Prev
    Next
    INDEX
    Explanations

    references to assembly attributes in programming and biochemical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Havolalar
    -0.59
     مواليد
    -0.53
    closePath
    -0.52
     मौ
    -0.49
    øst
    -0.48
     catég
    -0.47
    StreetMap
    -0.47
     ADVISORY
    -0.46
     directos
    -0.45
     hvil
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    1.00
    WebServlet
    0.77
     OnInit
    0.70
     Norway
    0.70
     Noruega
    0.69
    MigrationBuilder
    0.68
     ';
    
    0.67
    
    0.65
    ThroughAttribute
    0.64
    UITableView
    0.64
    Activations Density 2.495%

    No Known Activations