© 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. 20-GEMMASCOPE-RES-16K
    6. 3168
    Prev
    Next
    INDEX
    Explanations

    entities related to geography and demographics

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

    geographical locations, especially country and regional names.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.44
     Tortoise
    -0.41
     ब्रेकडाउन
    -0.40
    🧱
    -0.40
    Jefferson
    -0.39
     fusil
    -0.39
     Jefferson
    -0.39
     propOrder
    -0.39
    hical
    -0.39
    AsUp
    -0.38
    POSITIVE LOGITS
     remotely
    0.48
    InternalFrame
    0.45
    远程
    0.45
     remote
    0.45
     overseas
    0.45
     Outside
    0.43
    REMOTE
    0.43
     visiting
    0.42
     outside
    0.42
    elemField
    0.42
    Activations Density 0.472%

    No Known Activations