© 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. 5877
    Prev
    Next
    INDEX
    Explanations

    references to stores or store-related concepts

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

    references to digital or physical stores, with an emphasis on e-commerce and retail contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mentions of the stem for shops or memory-write operations, whether standalone or within plural, underscored, or compound forms.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "store" in technical/code contexts or as part of compound terms like "store_name" or "store_instructions".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
     AJAX
    -0.73
     Jac
    -0.69
     Hex
    -0.69
     OnInit
    -0.69
    NewGuid
    -0.67
     setw
    -0.66
     Hepatitis
    -0.65
    AccessException
    -0.65
     Jacobian
    -0.65
    hatic
    -0.65
    POSITIVE LOGITS
    Store
    1.09
     Store
    1.09
     store
    1.07
    store
    1.05
     STORE
    0.93
     createStore
    0.85
    getStore
    0.83
    STORE
    0.82
     Stores
    0.76
    stores
    0.74
    Activations Density 0.033%

    No Known Activations