Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4365
    Prev
    Next
    INDEX
    Explanations

    aspects of luxury real estate and property features

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

    buildings or construction

    np_acts-logits-general · gemini-2.0-flash

    property construction and features

    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
    binger
    -0.38
     meta
    -0.34
    ourge
    -0.32
     Theo
    -0.31
    Participating
    -0.30
     Participating
    -0.30
     publiek
    -0.30
    Origin
    -0.30
     puntas
    -0.30
    ubes
    -0.29
    POSITIVE LOGITS
     driveway
    0.73
     garage
    0.71
     Jacuzzi
    0.67
    acuzzi
    0.66
     jacuzzi
    0.66
    garage
    0.65
     garden
    0.65
     backyard
    0.65
     noDo
    0.64
     pool
    0.63
    Activations Density 0.192%

    No Known Activations