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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7182
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, concepts, and notation typically used in formal proofs or theorems

    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
    Kira
    -0.66
    op
    -0.62
     neta
    -0.61
    ki
    -0.60
     op
    -0.60
    mi
    -0.59
    g
    -0.57
    ta
    -0.56
    of
    -0.55
    readString
    -0.55
    POSITIVE LOGITS
    mn
    1.56
     mn
    1.17
     MN
    0.96
    MN
    0.94
     Mn
    0.94
    mnist
    0.94
    CloseOperation
    0.93
     محفوظة
    0.93
    SBATCH
    0.93
    WaitGroup
    0.86
    Activations Density 0.047%

    No Known Activations