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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16358
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific instrumentation and measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     EconPapers
    -0.52
    providedIn
    -0.52
     createSlice
    -0.52
    存于互联网档案馆
    -0.46
    Cyfeiriadau
    -0.46
     cherchés
    -0.46
     adquis
    -0.45
    RetentionPolicy
    -0.45
     proyec
    -0.43
    Partager
    -0.42
    POSITIVE LOGITS
    Instrumentation
    1.49
     Instrumentation
    1.34
     instrumentation
    1.20
    umented
    0.75
     instr
    0.75
    instrumental
    0.75
     Instr
    0.74
    instrument
    0.74
     INSTRUMENT
    0.72
    Instrumented
    0.68
    Activations Density 0.002%

    No Known Activations