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. 103082
    Prev
    Next
    INDEX
    Explanations

    occurrences of repeated patterns or structures in text

    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
     CURIAM
    -0.61
    AnchorStyles
    -0.59
    OGND
    -0.56
     AssemblyCulture
    -0.52
     betweenstory
    -0.52
    ValueGeneration
    -0.49
     EconPapers
    -0.47
    regelen
    -0.46
    tvguidetime
    -0.46
    Jeografia
    -0.44
    POSITIVE LOGITS
     >=",
    0.40
     BoxFit
    0.38
     HttpNotFound
    0.37
    탤
    0.37
    push
    0.35
     transférez
    0.35
    Fin
    0.35
    enak
    0.35
    TextHelper
    0.34
     himſelf
    0.34
    Activations Density 0.466%

    No Known Activations