© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4380
    Prev
    Next
    INDEX
    Explanations

    references to locations and institutions within a context

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

    Locations in northeast England

    np_acts-logits-general · gemini-2.0-flash

    newcastle and north east england

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.66
     SwitchCompat
    -0.66
     '\\;'
    -0.65
     estekak
    -0.64
    >{@
    -0.63
    Milwaukee
    -0.63
    SerializedName
    -0.63
     CreateTagHelper
    -0.62
     Milwaukee
    -0.62
    nocache
    -0.58
    POSITIVE LOGITS
     Newcastle
    1.10
    Newcastle
    0.98
     Northumberland
    0.92
     Tyne
    0.82
     Geor
    0.73
     Hadrian
    0.63
     Robson
    0.60
     Maitland
    0.58
    ersachsen
    0.58
     Collingwood
    0.57
    Activations Density 0.102%

    No Known Activations