© 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. 28-GEMMASCOPE-RES-16K
    11. 7887
    Prev
    Next
    INDEX
    Explanations

    cooking-related actions and ingredients

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

    layers or coverings

    np_acts-logits-general · gemini-2.0-flash

    layered or topped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.72
    LookAnd
    -0.65
    parsedMessage
    -0.62
    хьтан
    -0.60
    قایناقلار
    -0.56
    قایناق‌لار
    -0.56
    /**
    -0.53
     Autorizaciones
    -0.53
    __.__
    -0.51
     endwhile
    -0.50
    POSITIVE LOGITS
     сверху
    0.43
     Schicht
    0.40
     piled
    0.39
     cobertura
    0.37
     слой
    0.37
     covering
    0.37
     camada
    0.36
     layer
    0.36
     metade
    0.35
     poured
    0.35
    Activations Density 0.344%

    No Known Activations