© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6729
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to statistical models and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     v
    -0.46
     less
    -0.45
    ثيق
    -0.45
    oba
    -0.44
    ίνη
    -0.44
    ained
    -0.43
     w
    -0.43
    v
    -0.43
     gained
    -0.43
     bu
    -0.42
    POSITIVE LOGITS
     Efq
    0.96
     CreateTagHelper
    0.94
     myſelf
    0.87
    SharedDtor
    0.85
     ſeveral
    0.84
     Monfieur
    0.82
    IsMutable
    0.82
    Jereo
    0.81
     pleaſure
    0.80
     Majefty
    0.79
    Activations Density 1.042%

    No Known Activations