© 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. 4041
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate geographical or positional descriptions

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

    "location" or its variations

    np_acts-logits-general · gemini-2.0-flash

    places and positions

    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
    expandindo
    -0.66
    -------
    -0.64
    parsedMessage
    -0.63
     defaultstate
    -0.59
    :✨
    -0.55
     PREVIEW
    -0.53
    ViewFeatures
    -0.52
     CascadeType
    -0.52
     CURIAM
    -0.51
    PrototypeOf
    -0.51
    POSITIVE LOGITS
     Location
    0.77
     location
    0.74
    Location
    0.72
     LOCATION
    0.72
    location
    0.70
     Standort
    0.68
     locations
    0.67
     getLocation
    0.67
    LOCATION
    0.67
     Locations
    0.66
    Activations Density 0.187%

    No Known Activations