© 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. 5121
    Prev
    Next
    INDEX
    Explanations

    phrases related to limitations and insufficiencies

    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
     banget
    -0.55
     demais
    -0.45
     מאוד
    -0.45
     बहुत
    -0.44
     plenty
    -0.42
     muy
    -0.42
    過ぎて
    -0.42
     perfectamente
    -0.41
     rất
    -0.41
     جدًا
    -0.41
    POSITIVE LOGITS
     remotely
    1.47
     anywhere
    1.32
     NEAR
    1.16
     nearly
    1.15
    anywhere
    1.13
     near
    1.10
    nearly
    1.06
    near
    1.05
     Nearly
    1.04
    NEAR
    1.03
    Activations Density 0.391%

    No Known Activations