© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12316
    Prev
    Next
    INDEX
    Explanations

    references to central entities, such as institutions or concepts in health and finance

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

    "Central"

    np_acts-logits-general · gemini-2.0-flash

    central + entity/location/concept

    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
    Enllaces
    -0.68
     TextAppearance
    -0.68
    lankton
    -0.65
     Chwiliwch
    -0.64
     internacionales
    -0.63
     internacionais
    -0.62
     engraçadas
    -0.62
    GrantedAuthority
    -0.61
     Exter
    -0.61
     numberWith
    -0.60
    POSITIVE LOGITS
    central
    0.79
     central
    0.78
    Central
    0.76
     Central
    0.75
     CENTRAL
    0.73
    CENTRAL
    0.72
     nervous
    0.57
    — 
    0.53
    centr
    0.53
     centrale
    0.51
    Activations Density 0.081%

    No Known Activations