© 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. 13321
    Prev
    Next
    INDEX
    Explanations

    terms related to renovation and construction

    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
    DockStyle
    -0.48
    jgl
    -0.45
    Richie
    -0.43
     Chwiliwch
    -0.42
    tableFuture
    -0.40
     Richie
    -0.40
     parseFrom
    -0.39
     tableau
    -0.39
     getRule
    -0.38
    compli
    -0.38
    POSITIVE LOGITS
     renovation
    1.07
     renovations
    1.03
     Renovation
    1.01
     Renov
    1.01
    Renov
    0.97
     renovating
    0.91
     renovated
    0.90
     renovate
    0.88
     reno
    0.85
     renova
    0.85
    Activations Density 0.236%

    No Known Activations