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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6845
    Prev
    Next
    INDEX
    Explanations

    attributes associated with formality and design aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.72
    ValueStyle
    -0.69
    windowFixed
    -0.66
    MessageTagHelper
    -0.63
     виправивши
    -0.61
    hoeddwyd
    -0.59
    expandindo
    -0.59
     ErrIntOverflow
    -0.56
    ImageContext
    -0.55
    Tembelea
    -0.54
    POSITIVE LOGITS
     cold
    0.59
     austere
    0.56
     coldly
    0.54
     Cold
    0.52
    cold
    0.49
    Cold
    0.47
     Dry
    0.46
     Crisp
    0.46
     froide
    0.46
     spartan
    0.46
    Activations Density 1.036%

    No Known Activations