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. 5-GEMMASCOPE-RES-16K
    6. 2527
    Prev
    Next
    INDEX
    Explanations

    references to server instances and related errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.80
    InteropServices
    -0.80
     taches
    -0.78
     UIAlert
    -0.73
    ➡
    -0.73
     awakeFromNib
    -0.73
    canActivate
    -0.70
     Tade
    -0.70
     pathlib
    -0.66
     INTERESAR
    -0.66
    POSITIVE LOGITS
     servers
    2.18
     server
    2.17
     Server
    2.09
     Servers
    1.99
    Server
    1.98
    server
    1.97
     SERVER
    1.91
    SERVER
    1.84
    Servers
    1.73
     serveur
    1.60
    Activations Density 0.080%

    No Known Activations