© 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. 39-GEMMASCOPE-RES-16K
    11. 1194
    Prev
    Next
    INDEX
    Explanations

    mentions of systems or structures related to transportation and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    from
    -0.32
     tweeted
    -0.27
     lastly
    -0.26
    żd
    -0.25
     complained
    -0.24
    tableWidget
    -0.23
    another
    -0.23
     presso
    -0.22
     please
    -0.22
     gestorben
    -0.22
    POSITIVE LOGITS
     capabilities
    1.06
    Datuak
    1.05
     situation
    1.02
     możliwości
    1.02
     efforts
    1.01
     ability
    1.01
     possibilities
    1.01
    situation
    1.01
    queness
    1.00
     behavior
    0.99
    Activations Density 2.511%

    No Known Activations