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. 6569
    Prev
    Next
    INDEX
    Explanations

    specific entities related to data management, documentation, and quality assurance

    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
    ſelves
    -0.68
    databind
    -0.64
     Inscrivez
    -0.60
    usermodel
    -0.60
     Diſ
    -0.60
     ddelweddau
    -0.60
    SOUNDBITE
    -0.60
    <caption>
    -0.60
    gameserver
    -0.60
     pleaſure
    -0.60
    POSITIVE LOGITS
     they
    2.25
     we
    2.21
     you
    1.80
     that
    1.64
     he
    1.60
     she
    1.40
     они
    1.22
    they
    1.22
     THEY
    1.19
     I
    0.98
    Activations Density 2.369%

    No Known Activations