© 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. 38-GEMMASCOPE-RES-16K
    11. 8320
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics within the text

    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
     autorytatywna
    -0.49
     AssemblyCompany
    -0.48
     propOrder
    -0.47
    OCCURRED
    -0.46
     pleaſure
    -0.45
    AutoField
    -0.41
    Forty
    -0.41
    二十
    -0.41
     ocasião
    -0.41
     NavController
    -0.40
    POSITIVE LOGITS
     thousands
    1.21
    thousands
    1.10
     thousand
    1.09
     Thousands
    1.07
    Thousands
    1.05
    三千
    0.98
     THOUS
    0.98
     Thousand
    0.92
    一千
    0.89
    thousand
    0.86
    Activations Density 1.003%

    No Known Activations