© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11164
    Prev
    Next
    INDEX
    Explanations

    contexts related to social and economic issues, particularly focusing on jobs, debt, and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.78
     betweenstory
    -0.71
     CURIAM
    -0.67
    PyExc
    -0.60
    IVEREF
    -0.59
     deſſen
    -0.57
    ſſung
    -0.57
     $_"
    -0.57
     vooz
    -0.56
    <unused68>
    -0.56
    POSITIVE LOGITS
     merupakan
    0.96
     является
    0.85
    是他
    0.75
    才是
    0.75
    是最
    0.75
    เป็น
    0.74
    是我们
    0.73
    是我
    0.70
     adalah
    0.69
     menjadi
    0.69
    Activations Density 0.840%

    No Known Activations