© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11359
    Prev
    Next
    INDEX
    Explanations

    quantified contributions, statistics, and comparisons in various contexts

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

    "More/better" followed by "than"

    np_acts-logits-general · gemini-2.0-flash

    quantities, comparisons, and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forName
    -0.42
     سكانية
    -0.33
    ншот
    -0.31
    ➌
    -0.31
     useAuth
    -0.30
     gedaan
    -0.30
    Portail
    -0.28
    一层
    -0.28
     bepaalde
    -0.27
    一點
    -0.27
    POSITIVE LOGITS
     hundreds
    1.18
    hundreds
    1.08
     thousands
    1.08
     Hundreds
    1.02
     nearly
    0.99
    Hundreds
    0.98
     tens
    0.97
    thousands
    0.97
    超过
    0.94
    выше
    0.94
    Activations Density 0.362%

    No Known Activations