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. 13-GEMMASCOPE-RES-16K
    6. 10227
    Prev
    Next
    INDEX
    Explanations

    references to research methods and study design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.89
    脚注の使い方
    -0.84
    จึง
    -0.60
    Facades
    -0.60
    IVEREF
    -0.57
    +#+#
    -0.56
    carpus
    -0.56
    ERVIEW
    -0.55
    ]=>
    -0.55
    ándor
    -0.55
    POSITIVE LOGITS
    何より
    0.70
    CppMethod
    0.57
    そもそも
    0.53
     vulgares
    0.51
     also
    0.51
     сами
    0.49
    also
    0.49
     विश्वसनीयता
    0.48
     defaultstate
    0.48
     saites
    0.48
    Activations Density 0.842%

    No Known Activations