Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6751
    Prev
    Next
    INDEX
    Explanations

    the start of a document, specifically the beginning marker

    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
    存于互联网档案馆
    -1.11
     Efq
    -1.11
     myſelf
    -1.10
     houſe
    -1.10
     itſelf
    -1.09
     Monfieur
    -1.09
     pleaſure
    -1.08
    ſelf
    -1.08
    ſelves
    -1.04
     Majefty
    -1.02
    POSITIVE LOGITS
    te
    0.58
    \\
    0.55
    ↵
    0.49
    y
    0.49
    ↵↵
    0.49
     
    0.46
    n
    0.46
    x
    0.46
    ise
    0.45
    c
    0.45
    Activations Density 0.161%

    No Known Activations