© 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. 31-GEMMASCOPE-RES-16K
    11. 15110
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to software and systems requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conditional statements or logical necessity ("in order to," "must," "would need to").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.57
     utafitiHapana
    -0.56
    ViewImports
    -0.52
    MemoryWarning
    -0.51
     Wicidata
    -0.50
     Numerade
    -0.48
    ChildScrollView
    -0.47
     Wiktionnaire
    -0.47
     contextLoads
    -0.47
    いただけ
    -0.46
    POSITIVE LOGITS
     must
    2.88
    must
    2.45
    Must
    2.31
     Must
    2.30
     MUST
    1.98
    必须
    1.98
     måste
    1.95
     phải
    1.89
    ต้อง
    1.89
     need
    1.84
    Activations Density 2.273%

    No Known Activations