Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 12417
    Prev
    Next
    INDEX
    Explanations

    variables and their functions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Covid
    -1.33
     COVID
    -1.32
    . 
    -1.29
    COVID
    -1.26
    Covid
    -1.23
     covid
    -1.21
    https
    -1.14
     pandemia
    -1.12
    covid
    -1.10
     https
    -1.08
    POSITIVE LOGITS
     definately
    1.04
     idéia
    1.03
     ^_^
    1.03
     =)
    0.89
     -_-
    0.89
     biß
    0.86
     -.-
    0.86
     :]
    0.80
     wierd
    0.79
    myspace
    0.79
    Activations Density 0.750%

    No Known Activations