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. 6874
    Prev
    Next
    INDEX
    Explanations

    certain proper nouns and acronyms

    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
    MLLoader
    -0.67
    جوايز
    -0.66
    Personendaten
    -0.62
    transQ
    -0.57
    Jeografia
    -0.57
    Numerology
    -0.53
     Loeb
    -0.53
    enzio
    -0.52
    InitStructure
    -0.51
    lementation
    -0.51
    POSITIVE LOGITS
     mérit
    0.65
    первых
    0.60
    viewDidLoad
    0.59
    rizona
    0.57
     esimer
    0.56
     aikaa
    0.54
    ñora
    0.53
     myſelf
    0.53
     partag
    0.52
     impractica
    0.51
    Activations Density 0.327%

    No Known Activations