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. 3-GEMMASCOPE-RES-16K
    6. 10888
    Prev
    Next
    INDEX
    Explanations

    references to coding constructs and methods 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 @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.89
    esModule
    -0.82
    الإنجليزية
    -0.79
     useAppContext
    -0.73
    ClientSize
    -0.71
    StoryboardSegue
    -0.71
     pinulongan
    -0.70
    NegativeButton
    -0.67
    StreetMap
    -0.65
    +#+
    -0.64
    POSITIVE LOGITS
     nonatomic
    0.69
     Hongrie
    0.60
     muka
    0.51
    How
    0.49
     Kann
    0.49
     heb
    0.48
    ✨:
    0.47
    semp
    0.46
     çap
    0.46
    hen
    0.45
    Activations Density 0.321%

    No Known Activations