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. 3011
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to modeling and computation in a scientific or programming context

    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
     kasarigan
    -0.79
     Normdatei
    -0.74
    GraphicsUnit
    -0.62
    WithIOException
    -0.57
     EconPapers
    -0.56
    Tikang
    -0.56
     newOwner
    -0.56
     edn
    -0.56
     ErrIntOverflow
    -0.56
     contextLoads
    -0.55
    POSITIVE LOGITS
     param
    2.43
     parameter
    2.42
    param
    2.28
     Parameter
    2.25
     parameters
    2.20
     Param
    2.18
    parameter
    2.13
    Parameter
    2.10
    Param
    2.09
     params
    2.09
    Activations Density 0.252%

    No Known Activations