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. 2-GEMMASCOPE-RES-16K
    6. 8429
    Prev
    Next
    INDEX
    Explanations

    technical terms and code constructs related to programming and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.65
    RegressionTest
    -0.56
    UALA
    -0.49
    وفة
    -0.47
    illent
    -0.46
     retrouve
    -0.46
    itee
    -0.46
    Історія
    -0.46
    öz
    -0.46
    يكب
    -0.46
    POSITIVE LOGITS
    InstanceState
    0.88
    viewDidLoad
    0.66
     FontWeight
    0.64
    ंदीखरीदारी
    0.64
    GroupLayout
    0.62
     Lightboxes
    0.60
     estimés
    0.59
    textTheme
    0.58
    UnitTesting
    0.58
     استنادى
    0.56
    Activations Density 3.024%

    No Known Activations