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. 21-GEMMASCOPE-RES-16K
    6. 2518
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to timelines and durations of legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.36
    NECTION
    -0.35
     FontWeight
    -0.34
    illaries
    -0.34
    featureID
    -0.34
    filer
    -0.34
     ści
    -0.33
     걸
    -0.33
     nearly
    -0.32
     Belastung
    -0.32
    POSITIVE LOGITS
    WaitGroup
    0.64
     pinulongan
    0.63
     simplifié
    0.58
    Tembelea
    0.57
     ویکی‌پدی
    0.55
    WriteTagHelper
    0.52
    scriptcase
    0.51
    InitVars
    0.51
     linkovi
    0.50
     volant
    0.49
    Activations Density 0.757%

    No Known Activations