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. 21-GEMMASCOPE-RES-16K
    6. 14304
    Prev
    Next
    INDEX
    Explanations

    terms related to design and engineering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.54
     strerror
    -0.51
     विश्वसनीयता
    -0.45
    verages
    -0.44
    ésult
    -0.43
    *{-
    -0.42
    mamm
    -0.42
    abetes
    -0.41
    Билгалдахарш
    -0.41
    曖昧さ回避
    -0.40
    POSITIVE LOGITS
     designing
    0.89
     planning
    0.88
     design
    0.79
    Planning
    0.76
     Planning
    0.75
     planification
    0.75
    planning
    0.74
     diseñar
    0.71
     PLANNING
    0.71
     planners
    0.71
    Activations Density 0.695%

    No Known Activations