Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11288
    Prev
    Next
    INDEX
    Explanations

    terms related to visual aesthetics and design quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.59
     nakalista
    -0.59
    elemField
    -0.57
    AutoField
    -0.54
    complexContent
    -0.54
    الدراسه
    -0.53
    цездатний
    -0.52
    BASEPATH
    -0.50
     Audiodateien
    -0.49
     GenerationType
    -0.48
    POSITIVE LOGITS
     beautiful
    2.41
     beauty
    2.28
    beautiful
    2.27
     Beautiful
    2.25
    Beautiful
    2.16
     BEAUTIFUL
    2.09
     aesthetically
    2.06
     aesthetic
    2.02
     gorgeous
    1.99
    beauty
    1.98
    Activations Density 0.697%

    No Known Activations