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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15602
    Prev
    Next
    INDEX
    Explanations

    comparative or reference phrases in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    appearing before or after "reference."

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.42
    fromCharCode
    -0.40
     bodyParser
    -0.33
    /**
    -0.31
    Pautan
    -0.29
    Parcelize
    -0.29
    tagHelperRunner
    -0.28
    ISSN
    -0.28
    folg
    -0.28
    bodyParser
    -0.27
    POSITIVE LOGITS
     reference
    2.22
    reference
    1.96
     Reference
    1.81
     REFERENCE
    1.80
    Reference
    1.74
     référence
    1.72
     referência
    1.70
     referencia
    1.70
    REFERENCE
    1.59
     baseline
    1.58
    Activations Density 1.315%

    No Known Activations