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. 7-GEMMASCOPE-RES-16K
    6. 6579
    Prev
    Next
    INDEX
    Explanations

    components or settings related to user interface elements in a graphical application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.67
     betweenstory
    -0.59
    ":[{
    -0.50
    <eos>
    -0.50
    -0.49
     yana
    -0.49
    ịnh
    -0.48
    appendChild
    -0.48
    <
    -0.48
    Rohy
    -0.47
    POSITIVE LOGITS
    HasBeenSet
    0.90
    BibitemShut
    0.82
     Arkivert
    0.82
    consulté
    0.81
    الحياه
    0.78
    ']))
    
    0.78
    esModule
    0.77
    berdayakan
    0.76
     Diarsipkan
    0.76
     оригіналу
    0.75
    Activations Density 0.035%

    No Known Activations