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. 14891
    Prev
    Next
    INDEX
    Explanations

    mentions of online discussion platforms

    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
     pleaſure
    -0.82
    moiselle
    -0.64
    页面存档备份
    -0.63
     Carbon
    -0.63
    🏾
    -0.63
     disponibilités
    -0.61
    Carbon
    -0.60
     carbon
    -0.59
     ddelweddau
    -0.59
     Jefus
    -0.58
    POSITIVE LOGITS
     Forum
    1.28
     forum
    1.22
    Forum
    1.20
     FORUM
    1.13
    forum
    1.13
    interference
    1.10
     Interference
    1.09
     interference
    1.09
     Forums
    1.04
     forums
    0.99
    Activations Density 0.105%

    No Known Activations