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. 5-GEMMASCOPE-RES-16K
    6. 14289
    Prev
    Next
    INDEX
    Explanations

    mentions of healthcare providers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JLabel
    -0.87
    LoadScene
    -0.84
     HttpStatus
    -0.83
     calendriers
    -0.76
     JTextArea
    -0.74
     JButton
    -0.73
     JAS
    -0.73
    SerializedName
    -0.72
     KeyCode
    -0.72
     imageNamed
    -0.71
    POSITIVE LOGITS
    Provider
    2.12
     provider
    2.08
     Provider
    1.99
     providers
    1.99
    provider
    1.94
     Providers
    1.85
    providers
    1.82
    Providers
    1.76
    PROVIDER
    1.60
     proveedor
    1.29
    Activations Density 0.041%

    No Known Activations