© 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. 28-GEMMASCOPE-RES-16K
    11. 8310
    Prev
    Next
    INDEX
    Explanations

    JavaScript and React component code snippets involving state management and rendering logic

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

    Code snippets and HTML artifacts

    np_acts-logits-general · gemini-2.0-flash

    code punctuation symbols

    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
    可不
    -0.25
    座
    -0.25
     L
    -0.25
    /*
    -0.25
     mark
    -0.24
     gab
    -0.24
    vi
    -0.24
    supp
    -0.23
     super
    -0.23
     เย
    -0.23
    POSITIVE LOGITS
     kaarangay
    0.81
     propOrder
    0.80
     verſch
    0.79
    principalTable
    0.76
     geſch
    0.76
     فريبيس
    0.75
    majánló
    0.73
     ſont
    0.73
     laſſen
    0.72
    뀜
    0.72
    Activations Density 0.078%

    No Known Activations