© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8816
    Prev
    Next
    INDEX
    Explanations

    references to specific cities and geographical locations

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

    City names or related terms

    np_acts-logits-general · gemini-2.0-flash

    city names

    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
    出版年
    -0.59
    SBATCH
    -0.53
    VersionUID
    -0.51
    bootstrapcdn
    -0.49
    Pranala
    -0.45
     հղումներ
    -0.45
     createState
    -0.45
     estekak
    -0.45
    Tikang
    -0.45
    BibitemShut
    -0.44
    POSITIVE LOGITS
     city
    1.22
     City
    1.09
     CITY
    0.93
    City
    0.88
    市
    0.87
    city
    0.86
     getCity
    0.84
     mayor
    0.81
     Mayor
    0.79
     Stadt
    0.78
    Activations Density 0.404%

    No Known Activations