© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 5431
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to programming, evidence, and critical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsdelivr
    -0.55
    msgSender
    -0.52
     ffilm
    -0.49
     Piemonte
    -0.49
    kaar
    -0.48
    ilim
    -0.47
    pulumi
    -0.47
     dyn
    -0.47
     purpoſe
    -0.46
    WriteTagHelper
    -0.46
    POSITIVE LOGITS
    ℗
    0.67
     SwitchCompat
    0.65
     ChromeDriver
    0.62
     eventdata
    0.61
    λλά
    0.59
     AppCompatTheme
    0.57
     vendus
    0.57
    adaptiveStyles
    0.57
     doPost
    0.56
    ֹת
    0.56
    Activations Density 0.854%

    No Known Activations