© 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. 3768
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest a need for or involve extensive details or elaboration

    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
    RegressionTest
    -0.52
     surla
    -0.52
     Taktlose
    -0.52
    Rüyada
    -0.44
     الرياضيه
    -0.42
    NameInMap
    -0.39
    afficheront
    -0.39
     beginnetje
    -0.38
    efois
    -0.36
    argout
    -0.35
    POSITIVE LOGITS
     details
    3.70
     detail
    3.70
     Details
    3.28
    details
    3.23
     Detail
    3.19
    detail
    3.16
    Details
    3.08
    Detail
    2.95
     détails
    2.86
     DETAILS
    2.84
    Activations Density 1.035%

    No Known Activations