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. 1-GEMMASCOPE-RES-16K
    6. 13488
    Prev
    Next
    INDEX
    Explanations

    references to personal computers (PCs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.71
    UnsafeEnabled
    -0.66
     الحره
    -0.64
    stateProvider
    -0.63
    AutoScale
    -0.62
    PerformLayout
    -0.62
     téléphonique
    -0.61
    commutative
    -0.61
     AspNetCore
    -0.60
    ContentAsync
    -0.60
    POSITIVE LOGITS
    PC
    2.34
    pc
    2.28
     PC
    2.08
     pc
    1.86
    PCs
    1.64
     PCs
    1.45
    Pc
    1.45
     Pc
    1.34
    pcs
    1.08
     ПК
    1.06
    Activations Density 0.048%

    No Known Activations