© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13440
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly related to statistical models and distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.75
    tagHelperRunner
    -0.73
     utafitiHapana
    -0.66
    adaptiveStyles
    -0.65
     ligiloj
    -0.64
    Географиясе
    -0.64
    IsContent
    -0.62
    istoitu
    -0.62
    XmlAccessType
    -0.60
     GenerationType
    -0.59
    POSITIVE LOGITS
    th
    0.39
    itu
    0.37
    zeit
    0.35
    （
    0.35
    SE
    0.35
    ly
    0.35
    0
    0.34
    8
    0.34
    atrici
    0.34
    SS
    0.34
    Activations Density 0.941%

    No Known Activations