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

    Neuronpedia

    Jacobian LensNEW
    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. 2-GEMMASCOPE-RES-16K
    11. 2392
    Prev
    Next
    INDEX
    Explanations

    intensifiers or words that amplify the degree of an adjective or adverb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.66
    ImageContext
    -0.65
     INTERESAR
    -0.64
     queſta
    -0.61
     BoxFit
    -0.61
    TagMode
    -0.60
     dilap
    -0.59
     poichè
    -0.58
    ității
    -0.57
    lesse
    -0.56
    POSITIVE LOGITS
    <bos>
    0.37
     faixa
    0.30
    하다
    0.29
     (“
    0.29
     voire
    0.28
     قاشق
    0.28
    OrEqual
    0.28
    ,
    0.27
     собі
    0.27
    というか
    0.27
    Activations Density 0.534%

    No Known Activations