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. 117331
    Prev
    Next
    INDEX
    Explanations

    first-person plural pronouns and related expressions indicating collective actions or experiences

    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
    parsedMessage
    -0.97
    StructEnd
    -0.78
     ſte
    -0.77
     queſta
    -0.77
    Cyfeiriadau
    -0.77
     مشين
    -0.75
     resourceCulture
    -0.74
    RTSC
    -0.74
    SequentialGroup
    -0.73
     kasarigan
    -0.72
    POSITIVE LOGITS
     below
    0.42
     abajo
    0.39
     here
    0.36
     incele
    0.35
     answers
    0.35
     preguntas
    0.34
     brief
    0.34
     detailed
    0.34
    bardziej
    0.33
     Sitz
    0.33
    Activations Density 0.109%

    No Known Activations