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. 21-GEMMASCOPE-RES-16K
    6. 14228
    Prev
    Next
    INDEX
    Explanations

    biomedical terms related to substance use and treatment options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.87
    IVEREF
    -0.84
    SourceChecksum
    -0.81
    FTFY
    -0.80
    MessageTagHelper
    -0.75
    webElementXpaths
    -0.73
     purpoſe
    -0.72
     CreateTagHelper
    -0.71
    \"]
    -0.70
    Portály
    -0.69
    POSITIVE LOGITS
    etcode
    0.61
    ARDO
    0.58
    róleo
    0.57
    onViewCreated
    0.55
    AddHtmlAttribute
    0.54
    vetica
    0.54
     â
    0.54
    annica
    0.53
    λαμβ
    0.51
    TabIndex
    0.51
    Activations Density 1.175%

    No Known Activations