© 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. 10068
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court proceedings

    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
    oa̍t
    -0.85
    
    -0.83
    sizeCache
    -0.82
    EndGlobalSection
    -0.81
     $_(
    -0.81
    ⟬
    -0.80
     nahilalakip
    -0.79
    PreferredItem
    -0.79
    出版年
    -0.79
    featureID
    -0.77
    POSITIVE LOGITS
    1
    1.41
    2
    1.40
    3
    1.33
    4
    1.27
    5
    1.25
    7
    1.23
    6
    1.22
    9
    1.20
    8
    1.20
    0
    1.03
    Activations Density 1.979%

    No Known Activations