© 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. 15235
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a requirement or necessity for resources, actions, or conditions

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

    the word "require" and related technical constraints or prerequisites.

    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
    mybatisplus
    -0.51
     möjligt
    -0.50
     hopefully
    -0.45
     možné
    -0.45
     AssemblyVersion
    -0.45
     possibilities
    -0.44
     можли
    -0.43
     possible
    -0.43
    ophenol
    -0.43
     Paglinawan
    -0.43
    POSITIVE LOGITS
     special
    0.71
     especiais
    0.66
     careful
    0.65
     Requires
    0.62
    Requires
    0.61
    requires
    0.61
    特殊
    0.60
    特別な
    0.60
     специаль
    0.60
     disambiguazione
    0.60
    Activations Density 0.508%

    No Known Activations