© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6739
    Prev
    Next
    INDEX
    Explanations

    phrases related to banking and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    titleMargin
    -0.42
    :✨
    -0.35
    tinyos
    -0.33
    ̢
    -0.33
    Theorem
    -0.33
    yych
    -0.33
     Савезне
    -0.32
     '\\;'
    -0.32
    endpush
    -0.32
     Pristupljeno
    -0.32
    POSITIVE LOGITS
     account
    3.98
     accounts
    3.47
     Account
    3.31
    account
    2.94
     Accounts
    2.91
    Account
    2.89
     ACCOUNT
    2.88
    accounts
    2.66
    Accounts
    2.50
    ACCOUNT
    2.47
    Activations Density 0.456%

    No Known Activations