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. 21-GEMMASCOPE-RES-16K
    6. 732
    Prev
    Next
    INDEX
    Explanations

    references and citations to online resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })}$
    -0.47
    Бележки
    -0.46
    .
    -0.46
    </strong>
    -0.45
     
    -0.45
    )
    -0.44
     -
    -0.44
     &
    -0.44
     $\
    -0.44
    ose
    -0.41
    POSITIVE LOGITS
    ſelves
    0.92
     myſelf
    0.91
     houſe
    0.90
     оригіналу
    0.88
     itſelf
    0.88
    出版年
    0.86
     Waray
    0.86
     Majefty
    0.85
     pleaſure
    0.84
    ſelf
    0.84
    Activations Density 0.136%

    No Known Activations