© 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. 15-GEMMASCOPE-RES-16K
    11. 1913
    Prev
    Next
    INDEX
    Explanations

    mentions of significant historical events involving conflict or tragedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verk
    -0.42
    View
    -0.41
     dépens
    -0.41
     "
    -0.41
    공
    -0.40
    null
    -0.39
     AssemblyTitle
    -0.38
     spesa
    -0.38
    ad
    -0.37
     impuestos
    -0.37
    POSITIVE LOGITS
    DockStyle
    0.88
     Normdatei
    0.86
    WithIOException
    0.81
    ihnachten
    0.77
     Jefus
    0.76
     mergeFrom
    0.76
     ―――――
    0.75
     AssemblyCulture
    0.75
    __":
    0.75
     myſelf
    0.74
    Activations Density 0.278%

    No Known Activations