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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16214
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
     Bioinformatics
    -0.57
     Genomics
    -0.54
     PLoS
    -0.53
     genomics
    -0.53
     stakeholders
    -0.49
     DVD
    -0.45
     upfront
    -0.45
     stakeholder
    -0.45
     DVDs
    -0.45
     PLOS
    -0.45
    POSITIVE LOGITS
     GenerationType
    0.48
    ]")]
    0.47
     unpublished
    0.46
     navideñas
    0.45
    unpublished
    0.45
    AddressBook
    0.44
    (")
    0.44
     Probleme
    0.43
    contentLoaded
    0.43
    dota
    0.43
    Activations Density 0.791%

    No Known Activations