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. 9-GEMMASCOPE-RES-16K
    6. 15395
    Prev
    Next
    INDEX
    Explanations

    instances of LaTeX code related to mathematical or statistical formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.89
    },[])
    -0.80
     EClass
    -0.69
    TabbedPane
    -0.68
    таратура
    -0.65
    Vegeu
    -0.62
    oneofs
    -0.62
     diễn
    -0.62
     '\\;'
    -0.61
     himo
    -0.60
    POSITIVE LOGITS
     magasiner
    0.62
     SPIE
    0.56
     CreateTagHelper
    0.55
     vertes
    0.54
     numbers
    0.53
    Carriera
    0.53
    presto
    0.52
    c
    0.52
     kuf
    0.51
    addComponent
    0.51
    Activations Density 0.007%

    No Known Activations