© 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. 31-GEMMASCOPE-RES-16K
    11. 12621
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or establishments

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

    descriptive information about locations and facilities.

    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
    省市镇
    -0.30
     Ruß
    -0.27
     dessus
    -0.27
     stronę
    -0.26
    paramref
    -0.25
    ::$
    -0.25
     auxquels
    -0.24
    ष्ट
    -0.24
    żesz
    -0.24
    ſt
    -0.24
    POSITIVE LOGITS
     located
    2.97
    located
    2.61
     Located
    2.53
    Located
    2.48
     situated
    2.44
     ubicado
    2.13
     ubicada
    2.05
     situé
    2.00
     Situated
    1.99
    Situated
    1.95
    Activations Density 1.198%

    No Known Activations