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. 0-GEMMASCOPE-RES-16K
    6. 7778
    Prev
    Next
    INDEX
    Explanations

    references to various age groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*---
    -0.62
    Hozzáférés
    -0.61
    eqn
    -0.59
    Cyfeiriadau
    -0.58
     disambiguazione
    -0.57
    InputLabel
    -0.51
    ja
    -0.50
    行政区划
    -0.49
     nakalista
    -0.49
     favoritas
    -0.49
    POSITIVE LOGITS
    ages
    0.74
    MLLoader
    0.71
     propOrder
    0.70
    bring
    0.67
     bring
    0.65
     ages
    0.64
    itaine
    0.62
     */;
    0.62
     referenties
    0.59
    NOPQRST
    0.57
    Activations Density 0.148%

    No Known Activations