Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8473
    Prev
    Next
    INDEX
    Explanations

    references to events and celebrations, particularly parties or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.58
     CreateTagHelper
    -0.57
    transQ
    -0.56
    awtextra
    -0.55
    IntoConstraints
    -0.51
    ChildScrollView
    -0.50
    Хьажоргаш
    -0.49
     autorytatywna
    -0.49
    principalColumn
    -0.49
    optionalTypeArgs
    -0.49
    POSITIVE LOGITS
     complete
    2.42
    complete
    2.22
    Complete
    1.88
     Complete
    1.83
     COMPLETE
    1.82
     lengkap
    1.62
    COMPLETE
    1.61
     completa
    1.58
     completo
    1.52
     replete
    1.48
    Activations Density 0.639%

    No Known Activations