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. 20-GEMMASCOPE-RES-16K
    6. 751
    Prev
    Next
    INDEX
    Explanations

    specific numerical values associated with time or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下载附件
    -1.13
     utafitiHapana
    -0.92
    rungsseite
    -0.88
    enumi
    -0.87
     كومونز
    -0.84
    GEBURTSDATUM
    -0.83
    Portale
    -0.81
    ChildScrollView
    -0.80
    WaitGroup
    -0.80
     GenerationType
    -0.79
    POSITIVE LOGITS
    4
    0.93
    6
    0.92
    7
    0.90
    3
    0.89
    5
    0.88
    9
    0.88
    2
    0.87
    8
    0.86
    1
    0.81
    0
    0.80
    Activations Density 0.303%

    No Known Activations