© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 8216
    Prev
    Next
    INDEX
    Explanations

    references to official reports and forward-looking statements in a financial context

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

    SEC filings and company reports

    np_acts-logits-general · gemini-2.0-flash

    SEC filings and reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.52
     الحره
    -0.52
     propOrder
    -0.49
     pann
    -0.48
     bill
    -0.47
    \{\\
    -0.46
     taxation
    -0.46
     budget
    -0.45
     policy
    -0.45
     Budget
    -0.45
    POSITIVE LOGITS
     filing
    0.59
     SEC
    0.56
     filed
    0.54
     filings
    0.52
    regist
    0.51
    SEC
    0.51
    registered
    0.49
     unregistered
    0.48
     registered
    0.47
     registration
    0.47
    Activations Density 0.343%

    No Known Activations