© 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. 40-GEMMASCOPE-RES-16K
    11. 5408
    Prev
    Next
    INDEX
    Explanations

    specific coding phrases and structures typically found in programming or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.55
     utafitiHapana
    -0.49
    featureID
    -0.48
     مرئيه
    -0.48
    setupUi
    -0.47
     ComVisible
    -0.45
     مشين
    -0.43
     arşivlendi
    -0.43
    ništvo
    -0.41
    phazard
    -0.41
    POSITIVE LOGITS
     fr
    0.78
     NL
    0.77
    fr
    0.76
     RU
    0.76
     JP
    0.75
     nl
    0.74
     FR
    0.73
     ru
    0.73
    RU
    0.71
    FR
    0.71
    Activations Density 0.723%

    No Known Activations