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. 10-GEMMASCOPE-RES-16K
    6. 12647
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to synchronization and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -1.09
     autorytatywna
    -1.08
    AndEndTag
    -1.07
    sizeCache
    -1.06
     resourceCulture
    -1.01
     ویکی‌پدیای
    -0.94
     Normdatei
    -0.93
     صوتيه
    -0.90
     kasarigan
    -0.89
    =$?
    -0.89
    POSITIVE LOGITS
    teln
    0.43
     aasta
    0.42
    MAXN
    0.40
    okat
    0.39
     EX
    0.38
    루
    0.38
    laten
    0.37
    unix
    0.37
     such
    0.36
    UIView
    0.36
    Activations Density 2.039%

    No Known Activations