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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2307
    Prev
    Next
    INDEX
    Explanations

    financial transactions and accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jenost
    -0.42
     Kristina
    -0.42
    енча
    -0.41
    gulier
    -0.41
    hindu
    -0.40
    mení
    -0.40
    qtype
    -0.40
    setVerticalGroup
    -0.39
     papyrus
    -0.39
     Spectre
    -0.38
    POSITIVE LOGITS
     account
    2.03
     accounts
    1.84
    account
    1.66
     Account
    1.61
     Accounts
    1.49
    accounts
    1.49
     ACCOUNT
    1.48
    Account
    1.46
    Accounts
    1.30
     cuenta
    1.28
    Activations Density 0.150%

    No Known Activations