© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12660
    Prev
    Next
    INDEX
    Explanations

    references to packages and their summaries within data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.76
     becauſe
    -0.72
    Personendaten
    -0.72
     Monfieur
    -0.70
     itſelf
    -0.68
     ویکی‌پدی
    -0.67
    WaitGroup
    -0.67
     Efq
    -0.66
    MLLoader
    -0.66
     esternos
    -0.65
    POSITIVE LOGITS
    пта
    0.48
    getitem
    0.46
     indígenas
    0.46
    iyle
    0.45
     clé
    0.45
    getc
    0.45
    󠁢
    0.45
     stoichio
    0.45
     i
    0.44
     правило
    0.44
    Activations Density 0.025%

    No Known Activations