© 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. 24-GEMMASCOPE-RES-16K
    11. 879
    Prev
    Next
    INDEX
    Explanations

    positive expressions and compliments in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.59
     AssemblyTitle
    -0.58
     lenker
    -0.57
    UrlResolution
    -0.57
    disposing
    -0.54
    CodedInputStream
    -0.53
    expandindo
    -0.52
    JoinTable
    -0.52
     setTotal
    -0.50
    ItemBackground
    -0.50
    POSITIVE LOGITS
    :✨
    0.40
    Numerology
    0.39
    protoimpl
    0.38
    tvguidetime
    0.32
     sağ
    0.30
    orama
    0.30
     subjective
    0.30
     relevant
    0.30
    orre
    0.29
    发
    0.29
    Activations Density 0.133%

    No Known Activations