© 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. 23-GEMMASCOPE-RES-16K
    11. 5186
    Prev
    Next
    INDEX
    Explanations

    geographical locations and names of cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.78
    migrationBuilder
    -0.76
    providedIn
    -0.74
    SerializedName
    -0.73
    WriteBarrier
    -0.69
    mybatisplus
    -0.67
    ToBounds
    -0.66
    OpenHelper
    -0.64
    DIPSETTING
    -0.64
    protoimpl
    -0.63
    POSITIVE LOGITS
     suburb
    0.73
     initComponents
    0.72
     City
    0.72
     city
    0.70
     metropolitan
    0.66
     Metropolitan
    0.64
     metro
    0.63
     suburbs
    0.62
    based
    0.60
     Metro
    0.60
    Activations Density 0.251%

    No Known Activations