© 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. 37-GEMMASCOPE-RES-16K
    11. 3536
    Prev
    Next
    INDEX
    Explanations

    discussions of characteristics and advantages regarding specific entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.59
    RTLR
    -0.54
     utafitiHapana
    -0.50
     ModelExpression
    -0.46
     HttpNotFound
    -0.46
    Personendaten
    -0.45
     насељу
    -0.45
    raborty
    -0.44
    Aholisi
    -0.44
    setDo
    -0.44
    POSITIVE LOGITS
     characteristics
    2.70
    characteristics
    2.39
     Characteristics
    2.30
     traits
    2.28
     attributes
    2.27
     qualities
    2.19
    Characteristics
    2.16
     features
    2.08
     Eigenschaften
    2.06
     CHARACTERISTICS
    2.06
    Activations Density 1.711%

    No Known Activations