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. 2-GEMMASCOPE-RES-16K
    6. 6722
    Prev
    Next
    INDEX
    Explanations

    references to digital media, particularly e-commerce and e-books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.39
     myſelf
    -1.38
     himſelf
    -1.34
     itſelf
    -1.32
     ſeveral
    -1.31
     themſelves
    -1.29
     Monfieur
    -1.27
    ſelf
    -1.25
     Efq
    -1.24
     ―――――
    -1.22
    POSITIVE LOGITS
     e
    3.13
     E
    2.24
    e
    1.60
    E
    1.20
    getE
    1.18
     е
    1.14
     ई
    1.10
     O
    1.05
     o
    1.05
     ا
    1.02
    Activations Density 0.110%

    No Known Activations