© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4712
    Prev
    Next
    INDEX
    Explanations

    emotional responses and expressions of creativity or art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adversity or difficulty

    np_acts-logits-general · gemini-2.0-flash

    specific word followed by common phrase endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bolista
    -0.51
    surprise
    -0.49
    Surprised
    -0.48
     CURIAM
    -0.48
     surpris
    -0.47
    surprised
    -0.46
    Surprise
    -0.45
    ScopeManager
    -0.44
    RenderAtEndOf
    -0.43
     Guess
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.54
     torture
    0.46
     ModelExpression
    0.45
    devamını
    0.44
     nirvana
    0.43
     evil
    0.42
     existence
    0.42
    parsedMessage
    0.41
    でございます
    0.40
     glorious
    0.39
    Activations Density 0.534%

    No Known Activations