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. 14-GEMMASCOPE-RES-16K
    6. 4276
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic expression and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.73
    ValueStyle
    -0.69
    ExecuteReader
    -0.68
    WebMethod
    -0.65
    ölkerung
    -0.64
     CreateTagHelper
    -0.63
    AtIndexPath
    -0.63
    makeText
    -0.63
     histamine
    -0.63
    domésticos
    -0.61
    POSITIVE LOGITS
     depicting
    0.91
     artwork
    0.89
     artist
    0.86
     painting
    0.85
     depict
    0.84
     artistic
    0.79
     drawing
    0.78
     depictions
    0.77
     depiction
    0.77
    Artist
    0.76
    Activations Density 0.356%

    No Known Activations