© 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. 20-GEMMASCOPE-RES-16K
    11. 11354
    Prev
    Next
    INDEX
    Explanations

    console log statements in JavaScript code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.61
    €”
    -0.48
     territory
    -0.44
    躇
    -0.44
     Purchase
    -0.44
     Growth
    -0.43
     Product
    -0.43
    Gemeinden
    -0.43
     Grow
    -0.42
    พาะ
    -0.42
    POSITIVE LOGITS
    console
    0.84
    addGap
    0.66
     AssemblyTitle
    0.63
    printStackTrace
    0.58
    addPreferredGap
    0.58
     console
    0.58
    Fig
    0.57
    dafx
    0.55
    stdio
    0.54
    Console
    0.53
    Activations Density 0.039%

    No Known Activations