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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15011
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and procedural elements in judicial contexts

    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
     समीक्षक
    -0.54
    MLLoader
    -0.46
    ModelAdmin
    -0.44
    entieth
    -0.41
    ArgsConstructor
    -0.41
    AddTagHelper
    -0.39
    PARATUS
    -0.39
    ItemBackground
    -0.38
     DMS
    -0.38
    苻
    -0.36
    POSITIVE LOGITS
     Twelve
    1.74
    Twelve
    1.69
     twelve
    1.66
    twelve
    1.42
    十二
    1.31
     zwölf
    1.29
     twelfth
    1.27
     douze
    1.24
     XII
    1.21
     Twelfth
    1.21
    Activations Density 0.894%

    No Known Activations