© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 11982
    Prev
    Next
    INDEX
    Explanations

    phrases related to integration and becoming an essential part of various contexts or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ▔
    -0.38
    Personensuche
    -0.34
     joaat
    -0.33
    Begriffsklä
    -0.33
    abstractmethod
    -0.31
    KURZBESCHREIBUNG
    -0.31
    ContextCompat
    -0.30
    richTextPanel
    -0.29
    Provence
    -0.28
    Uninitialized
    -0.27
    POSITIVE LOGITS
     part
    3.69
    part
    2.91
     parte
    2.89
     часть
    2.73
     portion
    2.69
    Part
    2.50
     część
    2.48
     bagian
    2.45
     Teil
    2.36
    部分
    2.34
    Activations Density 3.339%

    No Known Activations