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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 988
    Prev
    Next
    INDEX
    Explanations

    technical terms related to manufacturing and robotic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     mergeFrom
    -0.64
     akar
    -0.63
     Boating
    -0.62
     ddelweddau
    -0.60
     réve
    -0.60
    summon
    -0.60
    TagMode
    -0.59
    LookAnd
    -0.59
    Jeografia
    -0.58
    mannian
    -0.58
    POSITIVE LOGITS
     conveyor
    0.84
     machine
    0.61
     throughput
    0.59
     automated
    0.58
     press
    0.56
     machines
    0.56
     processing
    0.54
     Convey
    0.54
     Förder
    0.53
     belt
    0.53
    Activations Density 0.594%

    No Known Activations