Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5689
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     становника
    -0.83
     betweenstory
    -0.82
    Jeografia
    -0.82
     Italijanski
    -0.79
    ьажоргаш
    -0.79
    OGND
    -0.77
    AddTagHelper
    -0.77
    richTextPanel
    -0.77
     ujednoznacz
    -0.76
    kháu
    -0.76
    POSITIVE LOGITS
     
    0.35
     convocatoria
    0.34
     dépla
    0.34
     petición
    0.33
     notícia
    0.32
     trámite
    0.30
     آماده
    0.29
     Vorsch
    0.29
     accro
    0.28
     invitación
    0.28
    Activations Density 0.554%

    No Known Activations