© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    phrases related to the methodology and assumptions in scientific proofs and analyses

    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
     LoggerFactory
    -0.49
     mérit
    -0.43
     résult
    -0.40
     Königin
    -0.39
     CONFIGURATION
    -0.39
     '{@
    -0.38
     dedicar
    -0.38
     actuels
    -0.38
    fromnode
    -0.37
     Tiefen
    -0.37
    POSITIVE LOGITS
     reform
    0.75
     construct
    0.69
     recast
    0.65
    MLLoader
    0.64
    reform
    0.61
     decompose
    0.61
     Reform
    0.59
    PreExecute
    0.57
     ModelExpression
    0.57
    construct
    0.56
    Activations Density 1.794%

    No Known Activations