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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2342
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions involving the process of making and preparing food or handling materials

    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
     purpoſe
    -0.74
    AnchorStyles
    -0.71
     pleaſure
    -0.68
     houſe
    -0.62
     preſent
    -0.60
     ſtate
    -0.57
     Monfieur
    -0.56
    lujah
    -0.56
     neceff
    -0.56
     abſ
    -0.55
    POSITIVE LOGITS
     CWE
    0.69
     HasFactory
    0.62
     BorderRadius
    0.62
    viewDidLoad
    0.62
    PostInfinity
    0.61
    IntoConstraints
    0.60
    setupUi
    0.59
     للمعارف
    0.58
     disambiguazione
    0.56
    Архівовано
    0.56
    Activations Density 0.424%

    No Known Activations