© 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. 14-GEMMASCOPE-RES-16K
    11. 10970
    Prev
    Next
    INDEX
    Explanations

    connections between various elements in a structured document or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.78
     snippetHide
    -0.68
    AndEndTag
    -0.65
    SharedCtor
    -0.61
     cherchés
    -0.59
     transfieras
    -0.59
     оригіналу
    -0.57
    Попис
    -0.57
    ьаж
    -0.56
     ujednoznacz
    -0.56
    POSITIVE LOGITS
     astore
    0.73
     then
    0.60
    twimg
    0.60
    AddTo
    0.53
    それを
    0.52
     Notting
    0.48
    Personendaten
    0.47
    ậy
    0.46
     put
    0.45
     Assemblies
    0.44
    Activations Density 0.538%

    No Known Activations